Glass plate wide flow online measurement and control method, system and device and electronic equipment

Abstract

The present application relates to the technical field of glass production, and discloses a glass plate width flow online measurement and control method, system, device and electronic equipment, which is applied to a glass forming process equipment, and comprises the following steps: collecting a glass liquid flow image and a glass original plate image of the glass forming process equipment; extracting a glass liquid bright edge of the glass liquid flow image and a glass original plate bright edge of the glass original plate image respectively; calculating a glass liquid flow variation based on the glass liquid bright edge; calculating a glass original visual width based on the glass original plate bright edge, and correcting the glass original visual width based on an original plate width correction coefficient to obtain a glass actual width; generating a control signal based on the glass liquid flow variation, and adjusting a flow channel gate opening degree of the glass forming process equipment based on the control signal to stabilize the glass liquid flow, so that the glass actual width tends to a target width. The present application solves the problems of large error and slow response existing in traditional manual control, and realizes high-precision closed-loop online measurement and control of the glass plate width and flow stability.

Description

Technical Field

[0001] This invention relates to the field of glass production technology, specifically to a method, system, device, and electronic equipment for online measurement and control of wide flow rate of glass plates. Background Technology

[0002] At the inlet of the tin bath, the molten glass has characteristics such as high temperature and high viscosity. Traditional flow detection methods cannot achieve automatic control of the flow channel gate due to accuracy issues. Manual adjustment of the gate results in large errors and poor real-time performance, which affects the production accuracy of the glass plate width. Summary of the Invention

[0003] This invention provides a method, system, device, and electronic equipment for online measurement and control of glass plate width flow rate, in order to solve the problems of the inability to achieve automatic control of the flow channel gate, the large errors and poor real-time performance caused by manual adjustment of the gate, which affect the production accuracy of glass plate width.

[0004] In a first aspect, the present invention provides a method for online measurement and control of wide flow rate of glass plates, applied to glass forming process equipment, the method comprising: Acquire images of molten glass flow and raw glass sheets from glass forming equipment; Extract the bright edges of the molten glass from the molten glass flow image and the bright edges of the original glass plate from the original glass plate image, respectively. Calculate the change in glass melt flow rate based on the bright edge of the glass melt; The original visual width of the glass is calculated based on the bright edge of the original glass plate, and the original visual width of the glass is corrected based on the original plate width correction coefficient to obtain the actual width of the glass. A control signal is generated based on the change in the glass melt flow rate, and the opening of the flow channel gate of the glass forming equipment is adjusted based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

[0005] This invention provides an online measurement and control method for glass plate width and flow rate. It simultaneously acquires images of the tin bath inlet and both sides of the transition roller table, extracting the bright edges of the molten glass from the molten glass flow image and the bright edges of the original glass plate from the original glass plate image. A high-precision algorithm is then used to directly calculate the change in molten glass flow rate and the original plate width. Combined with an original plate width correction coefficient, the accurate actual plate width is obtained. Based on this, the system generates a control signal according to the flow rate change, automatically and in real-time adjusting the opening of the flow channel gate. This effectively solves the problems of large errors and slow response in traditional manual control, achieving high-precision closed-loop online measurement and control of glass plate width and flow rate stability.

[0006] In one alternative embodiment, the glass forming process equipment includes a tin bath and a transition roller table; Images of the glass melt flow and the original glass sheet from the glass forming equipment were acquired, including: Images of the glass liquid flow on both sides of the tin bath inlet and images of the glass substrate on both sides of the transition roller table outlet were acquired.

[0007] In one optional implementation, the bright edges of the liquid glass in the liquid glass flow image and the bright edges of the original glass plate in the original glass plate image are extracted, respectively, including: The glass liquid flow image and the original glass plate image were preprocessed by grayscale conversion and noise reduction, and the preprocessed images were then sharpened to enhance edge features. The Canny edge detection operator is applied to the enhanced image. By calculating the gradient magnitude and direction, performing non-maximum suppression, and applying double threshold connection, continuous, single-pixel-wide glass liquid bright edges and glass original plate bright edges are finally extracted.

[0008] This invention provides an online measurement and control method for the width of a glass plate. Through grayscale conversion, noise reduction, and sharpening preprocessing, the image quality is effectively improved. Furthermore, by employing the Canny edge detection algorithm, which includes gradient calculation, non-maximum suppression, and dual threshold connection, subpixel-level, continuous, and accurate extraction of the bright edges of the molten glass and the original plate is achieved. This lays a reliable foundation for the subsequent accurate calculation of flow rate and width, and significantly improves the measurement accuracy and anti-interference capability of the overall system.

[0009] In one optional implementation, calculating the change in molten glass flow rate based on the bright edge of the molten glass includes: Determine the current position of each bright edge in the image coordinate system; The current position is compared with the preset reference zero point to calculate the corresponding position deviation. All position deviation values ​​are then summed to obtain the change in glass melt flow rate. The position deviation is calculated using the following formula: △X = △X1 + △X2; Where ΔX is the change in the flow rate of the molten glass, and ΔX1 and ΔX2 are the positional deviations between the current position and the preset reference zero position; where ΔX1 = X1 - X 10 △X2=X2-X 20 X1 and X2 are the current positions of each bright edge in the image coordinate system. 10 X2 is the preset reference zero position.

[0010] This invention provides an online measurement and control method for the flow rate of a glass plate. By directly comparing the real-time extracted bright edge position of the molten glass with a preset reference zero position and summing the differences, the change value reflecting the flow rate change is calculated. This method does not rely on the complex calibration of actual length and pixels, avoiding the errors introduced by the traditional calibration process. It realizes fast, high-precision and non-contact measurement of the flow rate change of molten glass, providing real-time and reliable data input for subsequent automatic control.

[0011] In one optional implementation, the original visual width of the glass is calculated based on the bright edge of the original glass plate, and the original visual width of the glass is corrected based on the original plate width correction coefficient to obtain the actual width of the glass, including: Determine the pixel position of the bright edge of the original glass plate in the image; Based on pixel position, the physical offset distance of the bright edge of the original glass plate on the measurement plane is calculated by optical geometric model to obtain the original visual width of the glass without thermal shrinkage compensation. The original visual width of the glass is corrected based on the original plate width correction factor to obtain the actual width of the glass. The original plate width correction factor is determined based on the thermal expansion characteristics of the glass, the thickness of the original plate, and the temperature difference between the measurement location and room temperature.

[0012] This invention provides an online measurement and control method for glass plate width flow rate. The original visual width of the glass is calculated directly from the image pixel position through an optical geometric model, avoiding complex on-site calibration. It also combines a comprehensive correction coefficient based on the glass's thermal properties, thickness, and temperature difference for automatic compensation, effectively overcoming measurement errors caused by temperature changes. This significantly improves the accuracy and adaptability of online measurement of the original glass plate width, especially ensuring the accuracy and reliability of width data when the plate is modified or operating conditions fluctuate.

[0013] In one alternative implementation, the original visual width of the glass is calculated using the following formula: W1=BY l -Y2; Where W1 is the original visual width of the glass, B is the horizontal distance between the measurement reference points, and Y... l Y1 is the physical offset distance between the bright edge of one side of the glass plate and the measurement reference point, and Y2 is the physical offset distance between the bright edge of the other side of the glass plate and the measurement reference point.

[0014] In one optional implementation, a control signal is generated based on the change in the glass melt flow rate, and the opening of the flow channel gate of the glass forming process equipment is adjusted based on the control signal to stabilize the glass melt flow rate, including: Based on the change in the flow rate of molten glass, an incremental PID algorithm is used to generate the control increment; Based on the control increment adjustment of the control output value, when the control output value exceeds the preset positive action threshold, a gate lowering control signal is generated and output; when the control output value is lower than the preset negative action threshold, a gate raising control signal is generated and output. The opening degree of the flow channel gate of the glass forming process equipment is adjusted based on the descent control signal or the rise control signal.

[0015] This invention provides an online measurement and control method for glass plate width flow rate. By employing an incremental PID algorithm based on the real-time acquired changes in glass liquid flow rate, the method achieves rapid and accurate calculation of the control signal and intelligently outputs gate lifting and lowering commands according to preset thresholds. This constructs a high-response-speed and high-stability automatic closed-loop control system for flow rate, completely replacing the traditional manual operation mode that relies on human experience, has a slow response, and large errors. This fundamentally improves the control accuracy and real-time performance of glass liquid flow rate and final plate width.

[0016] Secondly, this invention provides a wide-flow online measurement and control system for glass plates, applied to glass forming process equipment. The system includes: Image acquisition device, used to acquire images of molten glass flow and raw glass plates from glass forming equipment; An image processor extracts the bright edges of the molten glass from the image of the molten glass flow and the bright edges of the original glass plate from the image of the original glass plate, respectively. The controller is used to calculate the change in glass melt flow rate based on the bright edge of the glass melt; calculate the original visual width of the glass based on the bright edge of the original glass plate, and correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass; generate a control signal based on the change in glass melt flow rate, and adjust the opening of the flow channel gate of the glass forming process equipment based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

[0017] Thirdly, the present invention provides a wide-flow online measurement and control device for glass plates, applied to glass forming process equipment, the device comprising: The image acquisition module is used to acquire images of the glass liquid flow and the glass substrate from the glass forming process equipment. The image processing module is used to extract the bright edge of the molten glass from the image of the molten glass flow and the bright edge of the original glass plate from the image of the original glass plate, respectively. The flow detection module is used to calculate the change in the flow rate of molten glass based on the bright edge of the molten glass. The glass width measurement module is used to calculate the original visual width of the glass based on the bright edge of the original glass plate, and to correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass. The control module is used to generate control signals based on the changes in the glass melt flow rate, and to adjust the opening of the flow channel gate of the glass forming process equipment based on the control signals to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

[0018] Fourthly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the glass plate wide flow online measurement and control method of the first aspect or any corresponding embodiment described above.

[0019] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the glass plate wide flow online measurement and control method of the first aspect or any corresponding embodiment described above.

[0020] In a sixth aspect, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the glass plate wide flow online measurement and control method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of the online measurement and control method for wide flow of glass plate according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of the online measurement and control method for wide flow of glass plate according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the online measurement and control method for wide flow of glass plate according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the image processing flow in the online measurement and control method for wide flow of glass plates according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the tin bath inlet flow detection in the glass plate width flow online measurement and control method according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the glass plate width detection on both sides of the transition roller table in the online measurement and control method for glass plate width flow according to an embodiment of the present invention; Figure 8 This is a structural block diagram of a glass plate wide flow online measurement and control device according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] As an optional application scenario of this invention, such as Figure 1 As shown, this is a glass forming process equipment provided in an embodiment of the present invention. This glass forming process equipment is connected to a glass plate width flow online measurement and control system. The glass forming process equipment includes a tin bath 101, a transition roller table 102, and a gate 103. The tin bath 101 is connected to the transition roller table 102, and the flow channel gate 103 is installed on the glass liquid flow channel upstream of the inlet of the tin bath 101.

[0027] The tin bath is the core forming equipment. Here, high-temperature molten glass spreads, cools, and solidifies on the tin surface, forming a glass ribbon. The tin bath inlet receives the molten glass, whose flow rate is controlled by a flow channel gate. The tin bath outlet is directly connected to the beginning of the transition roller table, conveying the pre-solidified glass sheet to the transition roller table. Two cameras are installed on either side of the tin bath inlet to monitor the molten glass flow.

[0028] The transition roller table is a conveying and transition device. It receives the glass slabs from the tin bath and smoothly feeds them into the annealing furnace. The beginning of the transition roller table is directly connected to the outlet of the tin bath, and two cameras are installed on both sides of the transition roller table to measure the actual width of the formed glass slabs.

[0029] The gate is a key control mechanism. It regulates the flow rate of molten glass into the tin bath by raising and lowering. The gate is installed on the molten glass flow channel upstream of the tin bath inlet. The gate is controlled by a computer (image processor) in the online flow rate monitoring and control system for the tin bath. The computer uses the flow rate changes calculated by the tin bath inlet camera to drive the gate's raising and lowering motor via the control cabinet.

[0030] The wide-flow online measurement and control system for glass plates includes four cameras. Two cameras are installed on the left and right sides of the tin bath inlet, and the other two cameras are installed on the left and right sides of the transition roller table outlet. The four cameras are connected to a computer via an industrial Ethernet switch. The computer receives all image data and outputs switch signals to the gate control cabinet via a control board (such as PCL-725) to control the gate's movement. Images, data, curves, and the interface are displayed on a monitor. Figure 1 As shown, the windows displayed on the monitor include: left image window 1 at the solder bath inlet, right image window 2 at the solder bath inlet, left image window 3 at the transition roller table outlet, right image window 4 at the transition roller table outlet, board width and flow rate numerical curve window 5, manual / automatic gate indicator area 6, flow deviation area 7, original board measurement value 8, gate opening value 9, and machine time 10. The monitor also has a gate up button 11 and a gate down button 12.

[0031] In summary, this embodiment of the invention employs four digital high-definition network cameras, located on both sides of the transition roller table at the inlet and outlet of the tin bath. The computer reads the camera images via TCP / IP protocol, performs grayscale transformation, filtering enhancement, edge detection, and feature extraction to capture images of the bright edges of the glass. Combining parameters such as camera installation height, angle, and focal length, the original board width and flow rate change values ​​are calculated. This embodiment uses an Advantech PCL-733 board to read the encoder values ​​of the flow channel gate; based on the flow rate change values, the gate's PID (Proportional-Integral-Derivative Controller) is automatically adjusted. This embodiment also uses an Advantech PCL-725 board to output three switching signals to the flow channel gate control cabinet, controlling the gate's raising, lowering, and breaking alarm functions. All four cameras in this embodiment are CCD cameras.

[0032] According to an embodiment of the present invention, an embodiment of a method for online measurement and control of wide flow of a glass plate is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] This embodiment provides a method for online measurement and control of wide flow rate in glass plates, which can be used in the aforementioned glass forming process equipment. Figure 2 This is a flowchart of a glass plate wide-flow online measurement and control method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Acquire images of the glass liquid flow and the original glass plate from the glass forming equipment.

[0034] Specifically, the glass flow image refers to the image of the high-temperature, viscous, flowing molten glass (liquid state) on both sides of the inlet of the tin bath. The image shows a bright outline of the molten glass flow with edges that glow due to the high temperature (forming a "bright edge"), against a background that is usually dark refractory material or equipment structure. The glass flow image is used to monitor changes in the flow rate of the molten glass in real time and serves as a direct basis for automatically controlling the flow channel gate.

[0035] The glass sheet image refers to the solid glass strip that has been drawn from the tin bath and partially solidified at the exit of the transition roller table, but is still at a relatively high temperature; this is the glass sheet itself. The image shows a glass sheet with a fixed geometric shape and clear edges, with noticeable bright edges still visible due to residual heat. The glass sheet image is used to accurately measure the actual width of the glass sheet, serving as a basis for product quality monitoring and width control effectiveness verification.

[0036] Step S202: Extract the bright edge of the glass liquid from the glass liquid flow image and the bright edge of the glass original plate from the glass original plate image, respectively.

[0037] Specifically, the bright edge of the molten glass in the molten glass flow image refers to the bright outline formed by the contact between the free surface of the high-temperature, viscous molten glass and the refractory material. Due to the extremely high temperature (approximately 1100°C), the edge of the molten glass emits strong visible light, mainly due to the thermal radiation of the molten glass itself (high-temperature luminescence). The lateral movement of its position (ΔX) directly characterizes the change in the flow rate of the molten glass flowing into the tin bath and is the only direct input signal for the flow closed-loop control.

[0038] The bright edge of the glass plate in the image refers to the optical edge between the partially cured, solidified glass plate and the background (such as rollers or air). Because the glass still retains significant residual heat, its edge still exhibits a noticeable bright band. This is mainly due to the contrast between the glass plate and the background (such as the brightness / color difference between high-temperature glass and a room-temperature roller) and residual heat luminescence. Its fixed pixel position is used to calculate the physical width of the glass plate, serving as the basis for verifying product quality monitoring and control effectiveness.

[0039] Step S203: Calculate the change in glass melt flow rate based on the bright edge of the glass melt.

[0040] Specifically, by comparing the real-time extracted position of the bright edge of the molten glass with the preset reference zero position, the positional deviation of the bright edges of the molten glass on both sides is calculated and summed to directly obtain the ΔX value characterizing the change in molten glass flow rate, which serves as the core input signal for the automatic control flow channel gate.

[0041] Step S204: Calculate the original visual width of the glass based on the bright edge of the original glass plate, and correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass.

[0042] Specifically, the original visual width of the glass is a physical width value calculated directly from the CCD camera image and optical geometric model at the glass's current high-temperature state. That is, it is the physical dimension calculated using a geometric model based on the extracted bright edge pixel positions of the original glass plate, combined with known parameters such as the CCD camera's installation height, angle, and focal length. The original visual width of the glass is an intermediate calculation result, reflecting the instantaneous width of the glass at the measurement point (high temperature), but it does not yet consider the thermal contraction that occurs as the glass cools from high temperature to room temperature.

[0043] The original plate width correction factor is a proportional coefficient used to compensate for the shrinkage that occurs when glass cools from its high-temperature state at the time of measurement to room temperature. This factor is a value (usually slightly greater than 1) determined through theoretical calculations or empirical calibration, based on factors such as the thermal expansion characteristics of the glass, the actual thickness of the original plate, and the temperature difference between the measurement location (transition roller table) and room temperature. This factor can be set and adjusted in the software interface (i.e., the display). The original plate width correction factor is a compensation factor whose purpose is to correct the "width measured at high temperature" to the "finished width at room temperature," i.e., the actual width of the glass.

[0044] Step S205: A control signal is generated based on the change in the glass melt flow rate, and the opening of the flow channel gate of the glass forming process equipment is adjusted based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

[0045] Specifically, the control signal refers to the process of using the real-time calculated change in the flow rate of molten glass (ΔX) as the sole input, and then using an incremental PID control algorithm to automatically generate electronic commands (such as up / down switching signals) to drive the flow channel gate actuator.

[0046] The generated control signal (rising / falling pulse) is sent to the drive mechanism (such as a motor or hydraulic actuator) of the flow channel gate, causing it to precisely rise or fall according to instructions, thereby changing the size of the flow channel opening and realizing real-time, automatic adjustment of the flow rate of molten glass flowing into the tin bath. Its core logic is to ensure that the width of the final formed glass plate remains stable by stabilizing the inlet flow rate as the "source".

[0047] The target width refers to the precise physical width (unit: millimeters) that the finished glass product should achieve at room temperature, as set in the production process requirements or product order specifications. The target width is the ultimate setting benchmark and evaluation standard for the entire control system, and it is the ultimate goal of all control actions, which is to make the measured "actual glass width" as close as possible to and stable near the "target width".

[0048] The online measurement and control method for glass plate width and flow rate provided in this embodiment synchronously acquires images of the tin bath inlet and both sides of the transition roller table, and extracts the bright edge of the molten glass in the molten glass flow image and the bright edge of the original glass plate in the original glass plate image, respectively. Then, a high-precision algorithm is used to directly calculate the change in molten glass flow rate and the original plate width value. Combined with the original plate width correction coefficient, the accurate actual plate width is obtained. Based on this, the system generates a control signal based on the change in flow rate to automatically and in real time adjust the opening of the flow channel gate, thereby effectively solving the problems of large error and slow response in traditional manual control, and realizing high-precision closed-loop online measurement and control of glass plate width and flow rate stability.

[0049] This embodiment provides a method for online measurement and control of wide flow rate in glass plates, which can be used in the aforementioned glass forming process equipment. Figure 3 This is a flowchart of a glass plate wide-flow online measurement and control method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Acquire images of the glass liquid flow and the original glass plate from the glass forming equipment.

[0050] Specifically, the glass forming process equipment includes a tin bath and a transition roller table; the above step S301 includes: Step a: Collect images of the glass liquid flow on both sides of the tin bath inlet and images of the glass substrate on both sides of the transition roller table outlet.

[0051] Specifically, a CCD camera (Charge-Coupled Device Camera) is installed on each of the left and right sides of the tin bath inlet to synchronously acquire edge images of the high-temperature molten glass flow in order to obtain molten glass flow images for calculating flow rate changes.

[0052] On the left and right sides of the transition roller table exit, a CCD camera is installed to simultaneously capture images of the edge of the formed glass plate to obtain images of the glass plate for measuring the actual width.

[0053] Step S302: Extract the bright edge of the glass liquid from the glass liquid flow image and the bright edge of the glass original plate from the glass original plate image, respectively.

[0054] Specifically, the image processing flowchart is as follows: Figure 5As shown, the above step S302 includes: Step S3021, respectively perform preprocessing including grayscale conversion and noise reduction on the molten glass flow image and the original glass sheet image, and perform sharpening processing on the preprocessed images to enhance edge features.

[0055] Specifically, the embodiment of the present invention adopts image enhancement based on second-order differential, and the Laplacian operator to achieve image filtering and sharpening. The specific software implementation manners include: 1) Install the class library encapsulated with the Gaussian filtering operator; 2) Set parameters of the Gaussian filtering template; 3) Set the output temporary object of the video frame.

[0056] 4) Write the filtering sharpening function Filter(), the mathematical model formula is expressed as follows: (1); Wherein, x and y are respectively the distances from the center point in the horizontal and vertical directions, σ is the standard deviation, H(x,y) represents the Gaussian function, and f(x,y) is the image data (i.e., the molten glass flow image or the original glass sheet image).

[0057] 5) Perform filtering and sharpening operations frame by frame according to the refresh frequency, return the result to the temporary object, and perform cyclic calling continuously.

[0058] Step S3022, apply the Canny edge detection operator to the enhanced image, and finally extract the continuous, single-pixel wide bright edge of the molten glass flow and the bright edge of the original glass sheet by calculating the gradient magnitude and direction, performing non-maximum suppression, and applying double threshold connection.

[0059] Specifically, the embodiment of the present invention uses the Canny edge detection operator, taking extracting the bright edge of the original glass sheet as an example, the specific implementation method is as follows: 1) Calculate the magnitude and direction of the gradient by using the finite difference of the first-order partial derivative, obtain the change rate of grayscale jump near the edge by using the first-order convolution template, and calculate to obtain the extreme value.

[0060] 2) Perform non-maximum suppression on the gradient magnitude, set non-maximum values to zero, and obtain refined edges.

[0061] 3) Use the double threshold algorithm to detect and connect edges. First, set two thresholds T1 and T2 (T1<T2), so as to obtain the threshold edge images N1[i,j] and N2[i,j]. Mark the pixel points with gradient magnitude greater than the high threshold as strong edge points, and mark the pixel points with gradient magnitude between the high and low thresholds as weak edge points. Through edge connection, the strong and weak edge points are connected to form a complete edge, that is, the bright edge of the original glass sheet.

[0062] The methods for calculating gradient magnitude and non-maximum suppression are as follows: 1. Calculate the gradient using a 3×3 convolution kernel, and calculate the convolutions Gx and Gy in the x and y directions respectively: (2); (3).

[0063] 2. Gradient magnitude: Represents the magnitude of the gradient vector, reflecting the intensity of grayscale changes. The formula is as follows: (4); in, This represents the gradient magnitude.

[0064] 3. Gradient direction: This represents the direction of the gradient vector, i.e., the direction in which the gradient changes most rapidly. The formula is as follows: (5); in, Indicates the gradient direction.

[0065] 4. Non-maximum suppression: First, based on the direction of the gradient angle, compare the pixel with its two neighboring pixels at each pixel position. Then, determine whether the gradient magnitude of the current pixel is greater than or equal to those two neighboring pixels; if so, retain the pixel; otherwise, set it to zero.

[0066] Step S303: Calculate the change in molten glass flow rate based on the bright edge of the molten glass. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0067] Step S304: Calculate the original visual width of the glass based on the bright edge of the original glass plate, and correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass. For details, please refer to [link to details]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0068] Step S305: A control signal is generated based on the change in the glass melt flow rate, and the opening of the flow channel gate of the glass forming equipment is adjusted based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass approaches the target width. For details, please refer to [link to relevant documentation]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.

[0069] The online measurement and control method for glass plate width provided in this embodiment effectively improves image quality through grayscale conversion, noise reduction and sharpening preprocessing, and adopts the Canny edge detection algorithm, which includes gradient calculation, non-maximum suppression and dual threshold connection, to achieve sub-pixel level, continuous and accurate extraction of the bright edges of the glass liquid and the original plate. This lays a reliable foundation for the subsequent accurate calculation of flow rate and width, and significantly improves the measurement accuracy and anti-interference capability of the overall system.

[0070] This embodiment provides a method for online measurement and control of wide flow rate in glass plates, which can be used in the aforementioned glass forming process equipment. Figure 4 This is a flowchart of a glass plate wide-flow online measurement and control method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401: Acquire images of the molten glass flow and the original glass sheet from the glass forming equipment. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0071] Step S402: Extract the bright edges of the molten glass from the molten glass flow image and the bright edges of the original glass plate from the original glass plate image, respectively. For details, please refer to [link to relevant documentation]. Figure 3 Step S302 of the illustrated embodiment will not be described again here.

[0072] Step S403: Calculate the change in glass melt flow rate based on the bright edge of the glass melt.

[0073] Specifically, step S403 includes: Step S4031: Determine the current position of each bright edge in the image coordinate system.

[0074] Specifically, for each extracted bright edge, the horizontal coordinates of all pixels constituting the bright edge are statistically calculated within its horizontal search area to obtain a representative coordinate value that represents the overall horizontal position of the bright edge, which is used as its current position Xn in the image coordinate system (where Xn represents the left X1 or the right X2).

[0075] Step S4032: Compare the current position with the preset reference zero position, calculate the corresponding position deviation, and sum all position deviation values ​​to obtain the change in glass melt flow rate.

[0076] Specifically, such as Figure 6 As shown, two CCD cameras are installed on either side of the molten glass inlet to capture the edge of the molten glass flow. The two CCD cameras are positioned so that they have approximately the same field of view in the X direction (horizontal). During normal production, the current edge position of the glass is captured in the X direction from both the left and right fields of view. 10 X 20 Set as the reference zero point. When the width of the glass plate changes during production, set the glass plate edge distance to the reference zero point X.10 X 20 The changes are ΔX1 and ΔX2, then: Positional deviation is calculated using the following formula: △X = △X1 + △X2 (6); Where ΔX is the change in the flow rate of the molten glass, and ΔX1 and ΔX2 are the positional deviations between the current position and the preset reference zero position; where ΔX1 = X1 - X 10 △X2=X2-X 20 X1 and X2 are the current positions of each bright edge in the image coordinate system. 10 X2 is the preset reference zero position.

[0077] If ΔX increases, it is assumed that the glass melt flow rate increases. The control system then sends a gate descent signal to the flow channel gate control cabinet to lower the gate and reduce the glass melt flow rate. Conversely, if ΔX decreases, the control device sends a gate scaling signal to the flow channel gate control cabinet to raise the gate and increase the glass melt flow rate, thereby achieving the purpose of stabilizing the glass plate width.

[0078] Step S404: Calculate the original visual width of the glass based on the bright edge of the original glass plate, and correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass.

[0079] Specifically, step S404 includes: Step S4041: Determine the pixel position of the bright edge of the glass plate in the image.

[0080] Specifically, the schematic diagram for detecting the width of the glass plates on both sides of the transition roller table is as follows: Figure 7 As shown, for the bright edges of the extracted glass plates on the left and right sides, the feature pixel coordinates m1 and m2 representing the precise positions of each bright edge are obtained by performing positional statistical calculations on the discrete pixel set constituting the bright edge within its corresponding image area.

[0081] Step S4042: Based on the pixel position, calculate the physical offset distance of the bright edge of the original glass plate on the measurement plane using the optical geometric model to obtain the original visual width of the glass without thermal shrinkage compensation.

[0082] Specifically, the feature pixel coordinates m1 and m2 are input into a preset optical geometric model. Based on the known installation parameters of the corresponding CCD camera, including the installation height d (i.e., the distance between the optical center and the glass plate, with a measurement accuracy of millimeters), the angle β between the optical axis and the glass plate, and the lens focal length f, the model calculates the physical offset distance of the two glass edges on the measurement plane relative to the optical axis of the CCD camera. In this embodiment, the optical center is located 16mm from the target surface of the CCD camera along the optical center line.

[0083] The original visual width of the glass is calculated using the following formula: W1=BY l -Y2(7); Where W1 is the original visual width of the glass, B is the horizontal distance between the measurement reference points, and Y... l Y1 represents the physical offset distance between the bright edge of one side of the original glass plate and the measurement reference point, and Y2 represents the physical offset distance between the bright edge of the other side of the original glass plate and the measurement reference point. Wherein: Y l =m×w×d l × / ((f×n'-m×w×ctg(β1)×sin(β1))(8); Y2=m×w×d2× / ((f×n'-m×w×ctg(β2))×sin(β2))(9); Among them, Y l Y2 is the physical distance from the target object measurement point to the midpoint of the screen, negative from the midpoint outwards and positive from the midpoint inwards; m is the pixel distance from the target object image measurement point to the midpoint of the screen, negative from the midpoint outwards and positive from the midpoint inwards; f is the lens focal length; d is the vertical distance from the optical center to the glass plate; β1 and β2 are the angles between the optical axes of the left and right CCD cameras and the glass plate (unit: degrees × 10); n' is the full width of the CCD camera target surface in pixels along the calculation direction (n = 768 fixed value); w is the physical width of the full width of the CCD camera target surface along the calculation direction (this invention uses a 1 / 3-inch lens with a target surface size, w = 4.8mm fixed value).

[0084] Step S4043: Correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass; wherein, the original plate width correction coefficient is determined based on the thermal expansion characteristics of the glass, the thickness of the original plate, and the temperature difference between the measurement position and the room temperature.

[0085] Specifically, in this embodiment, a correction coefficient (thermal shrinkage coefficient) for the original glass width is added to the original glass width measurement software system at the transition roller table position. This coefficient is calculated by comprehensively considering factors such as glass thermal expansion and original glass thickness. The "original glass width measurement software system at the transition roller table position" refers to a collection of program modules and algorithms running on a computer (controller) specifically responsible for processing images from CCD cameras on both sides of the transition roller table and ultimately calculating the actual width of the glass.

[0086] Actual glass width = original visual width of glass × original panel width correction factor.

[0087] Step S405: A control signal is generated based on the change in the glass melt flow rate, and the opening of the flow channel gate of the glass forming process equipment is adjusted based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

[0088] Specifically, step S405 includes: Step S4051: Based on the change in glass melt flow rate, an incremental PID algorithm is used to generate the control increment.

[0089] Specifically, the incremental PID algorithm is an implementation of the Proportional-Integral-Derivative (PID) controller. Its core characteristic is that the algorithm outputs the increment or change in the control quantity (ΔOutput), rather than the absolute position value of the control quantity (Output). The incremental PID algorithm is the core decision-making component of the entire control loop. It receives the flow change ΔX as input deviation, performs internal calculations, and outputs a small control increment ΔY. n This increment is then added to the historical output value and, through threshold judgment, is ultimately converted into a specific "up" or "down" command for controlling the gate.

[0090] In this context, a PID control loop refers to a closed-loop control system based on the PID algorithm that can automatically and continuously adjust a physical quantity (such as temperature, flow rate, or pressure) to precisely stabilize it at a target value. In this embodiment, the PID control loop is used in an automatic adjustment system to stabilize the flow rate of molten glass. Its core logic is to sense deviations in real time, intelligently calculate and correct them, and continuously execute actions until the deviations are eliminated.

[0091] Furthermore, the change in glass melt flow rate ΔX obtained at the current sampling moment is set as the current deviation value E of the PID controller. n The current deviation value E n Together with the previous deviation value E n-1 Deviation value E from the previous two n-2 Substituting into the incremental PID calculation formula, the control increment ΔY is calculated. n : △Y n =(E n –E n-1 +En / Ki+(E n +E n-2 -2×E n-1 )×K d ) / K p (10); Among them, K p K i K d These are the proportional, integral, and derivative constants in the incremental PID algorithm, with a parameter range of 0.1~100.0, and ΔY. n To control the increment, E represents the calculated value (OUT value) of the PID control loop output at the nth sampling time. n、 E n-1、E n-2 These represent the deviations at the nth, (n-1)th, and (n-2)th sampling times, respectively.

[0092] Step S4052: Adjust the control output value based on the control increment. When the control output value exceeds the preset positive action threshold, generate and output a gate lowering control signal; when the control output value is lower than the preset negative action threshold, generate and output a gate raising control signal.

[0093] Specifically, the control increment △Y n The value is accumulated and added to the PID control loop output value Y from the previous moment to update and obtain a new control output value Y (which is a time function), i.e., Y = Y + ΔY. n The updated control output value Y is compared with preset positive action thresholds (e.g., +1) and negative action thresholds (e.g., -1): If Y > positive action threshold, a gate descent control signal (usually a fixed-width pulse or level signal) is generated and output, and then Y = Y - 1 is executed; If Y < negative action threshold, then generate and output a gate raising control signal, and then execute Y = Y + 1; If Y is between the two thresholds, no action signal will be output.

[0094] Step S4053: Adjust the opening degree of the flow channel gate of the glass forming process equipment based on the descent control signal or the rise control signal.

[0095] Specifically, the generated rise or fall control signal is sent to the electrical control cabinet of the flow channel gate via a control board (such as an Advantech PCL-725 card). After receiving the signal, the electrical control cabinet drives the gate's actuator (such as a motor) to move the gate in the corresponding direction (rise or fall) for a stroke corresponding to the signal duration, thereby changing the size of the flow channel opening and regulating the glass melt flow rate so that the actual width of the glass tends to the target width.

[0096] For example, the PID algorithm is executed according to the following instructions: E n =△X; △Y n =(E n –E n-1 +En / Ki+(E n +E n-2 -2×E n-1 )×K d ) / K p ; Y = Y + △Y n ; If Y > 1; Y = Y - 1; else if Y < -1; Y = Y + 1; The gate rises; End if.

[0097] The online measurement and control method for glass plate width and flow rate provided in this embodiment synchronously acquires images of the tin bath inlet and both sides of the transition roller table, and extracts the bright edge of the molten glass in the molten glass flow image and the bright edge of the original glass plate in the original glass plate image, respectively. Then, a high-precision algorithm is used to directly calculate the change in molten glass flow rate and the original plate width value. Combined with the original plate width correction coefficient, the accurate actual plate width is obtained. Based on this, the system generates a control signal based on the change in flow rate to automatically and in real time adjust the opening of the flow channel gate, thereby effectively solving the problems of large error and slow response in traditional manual control, and realizing high-precision closed-loop online measurement and control of glass plate width and flow rate stability.

[0098] This embodiment also provides a wide-range online flow measurement and control system for glass plates, such as... Figure 1 As shown, this system, applied to glass forming equipment, includes: An image acquisition device is used to acquire images of the glass liquid flow and the original glass plate from the glass forming process equipment; this image acquisition device is implemented by four CDD cameras.

[0099] An image processor extracts the bright edges of the molten glass from the image of the molten glass flow and the bright edges of the original glass plate from the image of the original glass plate, respectively. The controller is used to calculate the change in glass melt flow rate based on the bright edge of the glass substrate; calculate the original visual width of the glass based on the bright edge of the original glass substrate, and correct the original visual width of the glass based on the original substrate width correction coefficient to obtain the actual width of the glass; generate a control signal based on the change in glass melt flow rate, and adjust the opening of the flow channel gate of the glass forming process equipment based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width. The controller can be a computer, and an image processor is connected to the controller. In this embodiment, the image processor is implemented using image processing software and installed in the computer. Control boards PCL-725 and PCL-733 are also installed in the computer, and the control board PCL-725 is also connected to the flow channel gate control cabinet.

[0100] The glass plate wide-flow online measurement and control system also includes a display for showing images, data, curves, and interfaces, such as... Figure 1As shown, the windows displayed on the monitor include: left image window 1 at the solder bath inlet, right image window 2 at the solder bath inlet, left image window 3 at the transition roller table outlet, right image window 4 at the transition roller table outlet, board width and flow rate numerical curve window 5, manual / automatic gate indicator area 6, flow deviation area 7, original board measurement value 8, gate opening value 9, and machine time 10. The monitor also has a gate up button 11 and a gate down button 12.

[0101] The glass plate wide flow online measurement and control system provided in this embodiment of the invention can execute the glass plate wide flow online measurement and control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above components are the same as in the corresponding embodiments described above, and will not be repeated here.

[0102] This embodiment also provides a wide-flow online measurement and control device for glass plates, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0103] This embodiment provides a wide-range online flow measurement and control device for glass plates, which is applied to glass forming process equipment, such as... Figure 8 As shown, it includes: Image acquisition module 801 is used to acquire images of glass liquid flow and glass plate from glass forming equipment.

[0104] Image processing module 802 is used to extract the bright edge of the glass liquid in the glass liquid flow image and the bright edge of the glass plate in the original glass plate image, respectively.

[0105] The flow detection module 803 is used to calculate the change in the flow rate of the molten glass based on the bright edge of the molten glass.

[0106] The plate width measurement module 804 is used to calculate the original visual width of the glass based on the bright edge of the original glass plate, and correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass.

[0107] The control module 805 is used to generate a control signal based on the change in the glass melt flow rate, and adjust the opening of the flow channel gate of the glass forming process equipment based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

[0108] In some alternative embodiments, the glass forming process equipment includes a tin bath and a transition roller table; the image acquisition module 801 includes: The image acquisition unit is used to acquire images of the glass liquid flow on both sides of the tin bath inlet and images of the glass substrate on both sides of the transition roller table outlet.

[0109] In some alternative implementations, the image processing module 802 includes: The grayscale and sharpening unit is used to perform grayscale conversion and noise reduction preprocessing on the glass liquid flow image and the original glass plate image, respectively, and to sharpen the preprocessed image to enhance edge features.

[0110] The edge detection unit is used to apply the Canny edge detection operator to the enhanced image. By calculating the gradient magnitude and direction, performing non-maximum suppression, and applying double threshold connection, it finally extracts the continuous, single-pixel-wide bright edges of the liquid glass and the bright edges of the original glass plate.

[0111] In some alternative implementations, the flow detection module 803 includes: The current position determination unit is used to determine the current position of each bright edge in the image coordinate system.

[0112] The glass melt flow rate change calculation unit compares the current position with a preset reference zero position, calculates the corresponding position deviation, and sums all position deviation values ​​to obtain the glass melt flow rate change; wherein: the position deviation is calculated using the following formula: △X = △X1 + △X2; Where ΔX is the change in the flow rate of the molten glass, and ΔX1 and ΔX2 are the positional deviations between the current position and the preset reference zero position; where ΔX1 = X1 - X 10 △X2=X2-X 20 X1 and X2 are the current positions of each bright edge in the image coordinate system. 10 X2 is the preset reference zero position.

[0113] In some alternative implementations, the board width measurement module 804 includes: The pixel position determination unit is used to determine the pixel position of the bright edge of the glass plate in the image.

[0114] The original visual width calculation unit of the glass is used to calculate the physical offset distance of the bright edge of the original glass plate on the measurement plane based on the pixel position and through the optical geometric model, so as to obtain the original visual width of the glass without thermal shrinkage compensation.

[0115] The glass actual width calculation unit is used to correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass. The original plate width correction coefficient is determined based on the thermal expansion characteristics of the glass, the thickness of the original plate, and the temperature difference between the measurement position and the room temperature.

[0116] In some alternative implementations, the original visual width of the glass is calculated using the following formula: W1=BY l -Y2; Where W1 is the original visual width of the glass, B is the horizontal distance between the measurement reference points; Y l Y1 is the physical offset distance between the bright edge of one side of the glass plate and the measurement reference point, and Y2 is the physical offset distance between the bright edge of the other side of the glass plate and the measurement reference point.

[0117] In some alternative implementations, the control module 805 includes: The control increment calculation unit is used to generate control increments based on the change in glass melt flow rate using an incremental PID algorithm.

[0118] The control signal generation unit is used to adjust the control output value based on the control increment. When the control output value exceeds the preset positive action threshold, it generates and outputs a gate lowering control signal; when the control output value is lower than the preset negative action threshold, it generates and outputs a gate raising control signal.

[0119] An opening control unit is used to adjust the opening of the flow channel gate of a glass forming process equipment based on a descending control signal or an ascending control signal.

[0120] The glass plate wide flow online measurement and control device provided in this embodiment of the invention can execute the glass plate wide flow online measurement and control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments above, and will not be repeated here.

[0121] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0122] The following is a detailed reference. Figure 9 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 901, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 902 or a program loaded from memory 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device. The processor 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0123] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 9 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0124] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a memory 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it performs the functions defined in the glass plate wide flow online measurement and control method of the embodiments of the present invention.

[0125] Figure 9 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0126] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the glass plate wide-flow online measurement and control method shown in the above embodiments is implemented.

[0127] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0128] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for online measurement and control of wide flow rate using a glass plate, characterized in that, This equipment is used in glass forming processes. The glass forming process equipment includes a tin bath, a transition roller table, and a gate. The tin bath inlet receives molten glass with a flow rate controlled by the gate. The tin bath outlet is directly connected to the beginning of the transition roller table, conveying the pre-cured glass sheet to the transition roller table. Two cameras are installed on both sides of the tin bath inlet to monitor the flow of molten glass. Two cameras are installed on both sides of the transition roller table to measure the actual width of the formed glass sheet; the method includes: Acquire images of molten glass flow and raw glass sheets from glass forming equipment; Extract the bright edges of the molten glass from the molten glass flow image and the bright edges of the original glass plate from the original glass plate image, respectively. The change in glass melt flow rate is calculated based on the bright edge of the glass melt, including: Determine the current position of each of the bright edges in the image coordinate system; The current position is compared with a preset reference zero point to calculate the corresponding position deviation. All position deviation values ​​are then summed to obtain the change in glass melt flow rate. The position deviation is calculated using the following formula: △X = △X1 + △X2; Where ΔX is the change in the flow rate of the molten glass, and ΔX1 and ΔX2 are the positional deviations between the current position and the preset reference zero position; where ΔX1 = X1 - X 10 △X2=X2-X 20 X1 and X2 are the current positions of each bright edge in the image coordinate system. 10 and X 20 The preset reference zero position; The original visual width of the glass is calculated based on the bright edge of the original glass plate, and the original visual width of the glass is corrected based on the original plate width correction coefficient to obtain the actual width of the glass, including: Determine the pixel position of the bright edge of the original glass plate in the image; Based on the pixel position, the physical offset distance of the bright edge of the original glass plate on the measurement plane is calculated by optical geometric model to obtain the original visual width of the glass without thermal shrinkage compensation. The original visual width of the glass is corrected based on the original plate width correction factor to obtain the actual width of the glass; wherein, the original plate width correction factor is determined based on the thermal expansion characteristics of the glass, the thickness of the original plate, and the temperature difference between the measurement position and room temperature. A control signal is generated based on the change in the glass melt flow rate, and the opening of the flow channel gate of the glass forming process equipment is adjusted based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

2. The online flow measurement and control method for a wide glass plate according to claim 1, characterized in that, The glass forming process equipment includes a tin bath and a transition roller table; The acquisition of images of the glass liquid flow and the original glass plate from the glass forming process equipment includes: Images of the glass liquid flow on both sides of the tin bath inlet and images of the glass substrate on both sides of the transition roller table outlet were acquired.

3. The online flow measurement and control method for a wide glass plate according to claim 1, characterized in that, Extracting the bright edges of the molten glass in the molten glass flow image and the bright edges of the original glass plate in the original glass plate image, respectively, includes: The glass liquid flow image and the original glass plate image are respectively subjected to grayscale conversion and noise reduction preprocessing, and the preprocessed images are sharpened to enhance edge features; The Canny edge detection operator is applied to the enhanced image. By calculating the gradient magnitude and direction, performing non-maximum suppression, and applying double threshold connection, continuous, single-pixel-wide glass liquid bright edges and glass original plate bright edges are finally extracted.

4. The online flow measurement and control method for a wide glass plate according to claim 1, characterized in that, The original visual width of the glass is calculated using the following formula: W1=B-Y l -Y2; Where W1 is the original visual width of the glass, B is the horizontal distance between the measurement reference points, and Y... l Y1 is the physical offset distance between the bright edge of one side of the glass plate and the measurement reference point, and Y2 is the physical offset distance between the bright edge of the other side of the glass plate and the measurement reference point.

5. The online flow measurement and control method for a wide glass plate according to claim 1, characterized in that, Generating a control signal based on the change in the glass melt flow rate, and adjusting the opening of the flow channel gate of the glass forming process equipment based on the control signal to stabilize the glass melt flow rate, including: Based on the change in the glass melt flow rate, an incremental PID algorithm is used to generate the control increment; Based on the control increment, the control output value is adjusted. When the control output value exceeds the preset positive action threshold, a gate lowering control signal is generated and output; when the control output value is lower than the preset negative action threshold, a gate raising control signal is generated and output. The opening degree of the flow channel gate of the glass forming process equipment is adjusted based on the descent control signal or the rise control signal.

6. A wide-range online flow measurement and control system for glass plates, characterized in that, This equipment is used in glass forming processes. The glass forming process equipment includes a tin bath, a transition roller table, and a gate. The tin bath inlet receives molten glass with a flow rate controlled by the gate. The tin bath outlet is directly connected to the beginning of the transition roller table, conveying the pre-cured glass sheet to the transition roller table. Two cameras are installed on both sides of the tin bath inlet to monitor the flow of molten glass. Two cameras are installed on both sides of the transition roller table to measure the actual width of the formed glass sheet; the system includes: Image acquisition device, used to acquire images of molten glass flow and raw glass plates from glass forming equipment; An image processor extracts the bright edges of the liquid glass in the liquid glass flow image and the bright edges of the original glass plate in the original glass plate image, respectively. The controller is used to calculate the change in glass melt flow rate based on the bright edges of the glass melt, including: determining the current position of each bright edge in the image coordinate system; comparing the current position with a preset reference zero point, calculating the corresponding position deviation, and summing all position deviation values ​​to obtain the change in glass melt flow rate; wherein: the position deviation is calculated using the following formula: ΔX = ΔX1 + ΔX2; where ΔX is the change in glass melt flow rate, and ΔX1 and ΔX2 are the position deviations between the current position and the preset reference zero point; where ΔX1 = X1 - X 10 △X2=X2-X 20 X1 and X2 are the current positions of each bright edge in the image coordinate system. 10 and X 20 The process involves: setting a preset reference zero point; calculating the original visual width of the glass based on the bright edge of the original glass plate, and correcting the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass, including: determining the pixel position of the bright edge of the original glass plate in the image; calculating the physical offset distance of the bright edge of the original glass plate on the measurement plane based on the pixel position using an optical geometric model to obtain the original visual width of the glass without thermal shrinkage compensation; correcting the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass; wherein, the original plate width correction coefficient is determined based on the thermal expansion characteristics of the glass, the thickness of the original plate, and the temperature difference between the measurement position and room temperature; generating a control signal based on the change in the glass melt flow rate, and adjusting the opening of the flow channel gate of the glass forming process equipment based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

7. A wide-range online flow measurement and control device for glass plates, characterized in that, This equipment is used in glass forming processes. The glass forming process equipment includes a tin bath, a transition roller table, and a gate. The tin bath inlet receives molten glass with a flow rate controlled by the gate. The tin bath outlet is directly connected to the beginning of the transition roller table, conveying the pre-cured glass sheet to the transition roller table. Two cameras are installed on both sides of the tin bath inlet to monitor the flow of molten glass. Two cameras are installed on both sides of the transition roller table to measure the actual width of the formed glass sheet; the device includes: The image acquisition module is used to acquire images of the glass liquid flow and the glass substrate from the glass forming process equipment. The image processing module is used to extract the bright edge of the molten glass in the molten glass flow image and the bright edge of the original glass plate in the original glass plate image, respectively. The flow detection module is used to calculate the change in glass melt flow rate based on the bright edges of the glass melt, including: determining the current position of each bright edge in the image coordinate system; comparing the current position with a preset reference zero point, calculating the corresponding position deviation, and summing all position deviation values ​​to obtain the change in glass melt flow rate; wherein: the position deviation is calculated using the following formula: ΔX = ΔX1 + ΔX2; where ΔX is the change in glass melt flow rate, and ΔX1 and ΔX2 are the position deviations between the current position and the preset reference zero point; where ΔX1 = X1 - X 10 △X2=X2-X 20 X1 and X2 are the current positions of each bright edge in the image coordinate system. 10 and X 20 The preset reference zero position; The glass width measurement module is used to calculate the original visual width of the glass based on the bright edge of the original glass plate, and to correct the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass. This includes: determining the pixel position of the bright edge of the original glass plate in the image; calculating the physical offset distance of the bright edge of the original glass plate on the measurement plane based on the pixel position using an optical geometric model to obtain the original visual width of the glass without thermal shrinkage compensation; and correcting the original visual width of the glass based on the original plate width correction coefficient to obtain the actual width of the glass. The original plate width correction coefficient is determined based on the thermal expansion characteristics of the glass, the thickness of the original plate, and the temperature difference between the measurement location and room temperature. The control module is used to generate a control signal based on the change in the glass melt flow rate, and adjust the opening of the flow channel gate of the glass forming process equipment based on the control signal to stabilize the glass melt flow rate, so that the actual width of the glass tends to the target width.

8. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the online measurement and control method for wide flow of glass plates as described in any one of claims 1 to 5.

Images