Molten glass plate breakage detection regulation and control method and system, medium and electronic equipment

Abstract

The invention provides a glass liquid plate breakage detection regulation and control method and system, a medium and electronic equipment. The molten glass plate breakage detection regulation and control method comprises the following steps: acquiring continuous molten glass images by utilizing a plurality of industrial cameras; acquiring glass liquid boundary and glass liquid width data according to the glass liquid image; obtaining the actual width of the molten glass based on the boundary of the molten glass and the calibration parameters of the industrial camera; and performing width threshold judgment on the actual width of the molten glass, and adjusting the opening degree of a flow channel adjusting flashboard based on a judgment result. According to the broken glass plate detection and regulation method provided by the invention, the accuracy of glass liquid control can be improved.

Description

Technical Field

[0001] This application belongs to the technical field of glass production, and relates to a method, system, medium and electronic device for detecting and regulating the breaking of a glass liquid plate. Background Art

[0002] In the float glass production process, the tin bath is the core equipment, and its function is to receive the glass liquid melted from the kiln. The melted glass liquid flows into the tin bath through a special channel and floats on the surface of the molten tin liquid to form a uniform liquid film. In this process, the edge rollers ensure that the glass ribbon maintains a uniform thickness during the flow by making fine adjustments to the glass liquid. How to accurately control the flow and distribution of the glass liquid has become a key technology to ensure production efficiency and product quality. Summary of the Invention

[0003] The purpose of this application is to provide a method, system, medium and electronic device for detecting and regulating the breaking of a glass liquid plate, which is used to improve the accuracy of glass liquid control.

[0004] In a first aspect, this application provides a method for detecting and regulating the breaking of a glass liquid plate, and the method for detecting and regulating the breaking of a glass liquid plate includes: collecting continuous glass liquid images by using a plurality of industrial cameras; obtaining glass liquid boundary and glass liquid width data according to the glass liquid images; obtaining the actual width of the glass liquid based on the glass liquid boundary and the calibration parameters of the industrial cameras; making a width threshold judgment on the actual width of the glass liquid, and adjusting the opening degree of the regulating gate of the flow channel based on the judgment result.

[0005] In an implementation manner of the first aspect, the method for detecting and regulating the breaking of a glass liquid plate further includes: processing the glass liquid images to obtain a glass liquid region; processing the glass liquid region by using morphological operations to obtain enhanced features of the glass liquid; obtaining the connected regions of the glass liquid region by using a connected component analysis algorithm based on the enhanced features of the glass liquid; making a judgment and analysis on the parameter changes of the connected regions to obtain the glass liquid break-off situation.

[0006] In an implementation manner of the first aspect, the process of processing the glass liquid images to obtain a glass liquid region includes: preprocessing the glass liquid images to obtain pure glass liquid images; performing threshold segmentation on the pure glass liquid images to obtain a glass liquid region.

[0007] In an implementation manner of the first aspect, the process of making a judgment and analysis on the parameter changes of the connected regions to obtain the glass liquid break-off situation includes: analyzing the connected regions between adjacent image frames to obtain the parameter changes of the connected regions; making a threshold judgment on the parameter changes of the connected regions to obtain the glass liquid break-off situation.

[0008] In an implementation of the first aspect, the process of obtaining the actual width of the molten glass includes: extracting edge features from the molten glass image to obtain the pixel points of the upper edge and the lower edge of the molten glass; obtaining the pixel width of the molten glass according to the pixel points of the upper edge and the lower edge of the molten glass; and performing proportional conversion on the pixel width of the molten glass to obtain the actual width of the molten glass.

[0009] In an implementation of the first aspect, the method for detecting and regulating the breaking of the molten glass plate further includes: calibrating the industrial cameras by using the checkerboard calibration method to obtain the internal parameters and external parameters of the multiple industrial cameras; and converting the molten glass width data to the world coordinate system by using the external parameters.

[0010] In an implementation of the first aspect, the method for detecting and regulating the breaking of the molten glass plate further includes: performing weighted fusion processing on the molten glass width data in multiple consecutive frames of molten glass images to obtain the global width range of the molten glass.

[0011] In the second aspect, the present application provides a system for detecting and regulating the breaking of a molten glass plate, where the system for detecting and regulating the breaking of the molten glass plate includes: a molten glass image acquisition module, configured to collect consecutive molten glass images by using multiple industrial cameras; a data acquisition module, configured to obtain the molten glass boundary and the molten glass width data according to the molten glass image; an actual width acquisition module, configured to obtain the actual width of the molten glass based on the molten glass boundary and the calibration parameters of the industrial cameras; and a judgment and adjustment module, configured to perform width threshold judgment on the actual width of the molten glass and adjust the opening degree of the regulating gate of the flow channel based on the judgment result.

[0012] In the third aspect, the present application provides an electronic device, where the electronic device includes: a memory, on which a computer program is stored; and a processor, communicatively connected to the memory, configured to execute the computer program to implement the above-mentioned method for detecting and regulating the breaking of the molten glass plate.

[0013] In the fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by an electronic device, it implements the above-mentioned method for detecting and regulating the breaking of the molten glass plate.

[0014] As described above, the method, system, medium, and electronic device for detecting and regulating the breaking of the molten glass plate according to the present application have the following beneficial effects:

[0015] The glass liquid plate breaking detection and regulation method provided by this application can collect glass liquid images using multiple industrial cameras, process and analyze the boundaries and width of the glass liquid based on the calibrated industrial cameras to obtain the actual width of the glass liquid, judge the glass liquid and the glass liquid plate breaking detection situation through the width threshold, and adjust the gate opening of the flow channel according to the detection results. Description of the Drawings

[0016] Figure 1 It shows a schematic application scenario diagram of the glass liquid production system described in the embodiment of this application.

[0017] Figure 2 It shows a schematic process diagram of the glass liquid plate breaking detection and regulation method described in the embodiment of this application.

[0018] Figure 3 It shows a schematic process diagram of obtaining the glass liquid cut-off situation described in the embodiment of this application.

[0019] Figure 4 It shows a schematic process diagram of the glass liquid plate breaking detection and regulation method described in the embodiment of this application.

[0020] Figure 5 It shows a schematic structural diagram of the glass liquid plate breaking detection and regulation system described in the embodiment of this application.

[0021] Figure 6 It shows a schematic structural diagram of the electronic device described in the embodiment of this application.

[0022] Element Number Explanation

[0023] 1 Glass liquid plate breaking detection and regulation system

[0024] 11 Glass liquid image acquisition module

[0025] 12 Data acquisition module

[0026] 13 Actual width acquisition module

[0027] 14 Judgment and adjustment module

[0028] 2 Electronic device

[0029] 21 Memory

[0030] 22 Processor

[0031] 23 Display

[0032] Steps S11 - S14

[0033] Steps S21 - S24

[0034] Steps S500 to S513 Specific implementation manners

[0035] The following uses specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0036] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0037] In the float glass production process, the tin bath is the main equipment. The molten glass liquid in the kiln flows into the tin bath along the runner. The glass liquid floats on the surface of the tin liquid and is drawn into a glass ribbon with a uniform thickness by the edge rollers during its flow. The speed at which the glass liquid flows into the tin bath is an important influencing factor in the glass forming section. If the speed at which the glass liquid flows into the tin bath is too fast, it will cause too much glass liquid to accumulate in the tin bath, resulting in out-of-control thickness of the glass plate. If the speed at which the glass liquid flows into the tin bath is too slow, it is not conducive to the edge rollers drawing it into a uniform glass ribbon. Especially for the current production of high-end precision float glass production lines such as ultra-thin glass, the speed at which the glass liquid flows into the tin bath directly affects the product quality of the ultra-thin glass.

[0038] Currently, in order to prevent too much or too little glass liquid flowing from the kiln into the tin bath, a high-temperature resistant camera is usually installed at the entrance of the tin bath. Workers manually operate the lifting gate at the entrance of the tin bath to control the inflow speed of the glass liquid according to the spreading shape of the glass liquid shown on the industrial television. This solves the problem of excessive or insufficient glass liquid in the bath to a certain extent, but it is insufficient in terms of control accuracy and real-time performance.

[0039] At least for the above problems, the following embodiments of the present application provide a method for detecting and regulating the breakage of the glass liquid plate. The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings in the embodiments of the present application.

[0040] Figure 1 Shown is a schematic diagram of an application scenario of an embodiment of the present application. As Figure 1As shown in the figure, the glass liquid production system includes cameras 1-4, a runner gate, a plate width control module, and a plate width display module. Cameras 1-4 are arranged at different angles of the runner to monitor the flow state and width of the glass liquid in real time. The gate of the runner is used to adjust the flow rate of the glass liquid. The plate width control module automatically adjusts the opening degree of the gate according to the image data captured by the camera to maintain the glass liquid plate at the set width. The plate width display module can intuitively display the width information, enabling the operator to clearly understand the current width of the glass liquid and facilitating timely adjustment or decision-making.

[0041] Figure 2 It shows a schematic process diagram of the method for detecting and regulating the breakage of the glass liquid plate in an embodiment of the present application. As Figure 2 shown, the method for detecting and regulating the breakage of the glass liquid plate includes the following steps S11 to S14.

[0042] Step S11, collecting continuous glass liquid images by using multiple industrial cameras.

[0043] Exemplarily, continuous images of the glass liquid are obtained by combining multiple industrial cameras with image acquisition of OpenCV. The number of industrial cameras can be four, and the width change of the glass liquid is monitored in real time from different angles by the four industrial cameras.

[0044] Step S12, obtaining the glass liquid boundary and glass liquid width data according to the glass liquid images.

[0045] Exemplarily, the glass liquid boundary is the edge line formed when the glass liquid flows in the runner, and this line marks the boundary between the glass liquid and the surrounding environment or non-glass liquid area. The clarity of the glass liquid boundary can reflect the flow state and temperature distribution of the glass liquid. Controlling the boundary helps to prevent the glass liquid from overflowing in the runner or forming uneven thickness. The glass liquid width data is the width value of the cross-section of the glass liquid measured in the runner.

[0046] Step S13, obtaining the actual width of the glass liquid based on the glass liquid boundary and the calibration parameters of the industrial camera. The calibration parameters of the industrial camera are the parameters used to describe the imaging characteristics of the camera.

[0047] Step S14, performing a width threshold judgment on the actual width of the glass liquid, and adjusting the opening degree of the regulating gate of the runner based on the judgment result.

[0048] Exemplarily, the runner is a section of the channel in the glass production process, which is the path for the glass liquid to flow from the furnace to the forming machine. The gate opening degree refers to the opening size of the adjustable gate used to control the flow rate and width of the glass liquid in the runner. Adjusting the gate opening degree can change the flow rate and flow of the glass liquid through the runner.

[0049] According to the above description, it can be known that the glass liquid plate breaking detection and regulation method provided by this application can collect glass liquid images by using multiple industrial cameras, process and analyze the boundary of the glass liquid and the width of the glass liquid based on the calibrated industrial cameras to obtain the actual width of the glass liquid, judge the glass liquid and the glass liquid plate breaking detection situation through the width threshold, and adjust the gate opening of the flow channel according to the detection result.

[0050] Figure 3 It shows a schematic process diagram of obtaining the glass liquid cut-off situation in an embodiment of this application. As Figure 3 shown, the glass liquid plate breaking detection and regulation method includes the following steps S21 to S24.

[0051] Step S21, process the glass liquid image to obtain the glass liquid region.

[0052] Exemplarily, use the OpenCV image processing algorithm to preprocess the image, remove the interference noise in the glass liquid image, and separate the glass liquid region from the background of the glass liquid image through the threshold segmentation technology.

[0053] Among them, the process of processing the glass liquid image to obtain the glass liquid region includes the following steps S211 to S212.

[0054] Step S211, preprocess the glass liquid image to obtain a pure glass liquid image.

[0055] Exemplarily, preprocess the glass liquid image to obtain a pure glass liquid image by graying and smoothing the glass liquid image. Use the cvtColor function in OpenCV to convert the RGB image of the glass liquid image into a glass liquid grayscale image, and use the GaussianBlur function in OpenCV to perform Gaussian blur processing on the glass liquid grayscale image to obtain a pure glass liquid image.

[0056] Step S212, perform threshold segmentation on the pure glass liquid image to obtain the glass liquid region.

[0057] Exemplarily, use the threshol() function to perform threshold segmentation processing on the pure glass liquid image. If the gray value of the pixel point in the original pure glass liquid image is greater than 127, the gray value is set to 255; if the gray value of the pixel point in the original pure glass liquid image is less than 127, the gray value is set to 0.

[0058] Among them, the calculation of the gray value can be expressed as: 0.114*B + 0.587*G + 0.299*R

[0059] B represents blue, R represents red, and G represents green.

[0060] Step S22: Process the molten glass region using morphological operations to obtain enhanced features of the molten glass.

[0061] Exemplarily, use the morphological operations of OpenCV to enhance the features of the molten glass to obtain enhanced features of the molten glass.

[0062] Step S23: Based on the enhanced features of the molten glass, use the connected component analysis algorithm to obtain the connected components of the molten glass region.

[0063] Exemplarily, the connected components of the molten glass region are regions composed of a group of interconnected pixels. Within the connected region, each pixel is adjacent to at least one other pixel in the horizontal, vertical, and / or diagonal directions. Different connected regions are labeled through the connected component function, and statistical attributes such as the area and bounding box position within the region are calculated.

[0064] Step S24: Analyze and judge the parameter changes of the connected components to obtain the situation of molten glass flow interruption.

[0065] Among them, the process of analyzing and judging the parameter changes of the connected components to obtain the situation of molten glass flow interruption includes the following steps S241 to S242.

[0066] Step S241: Analyze the connected components between adjacent image frames to obtain the parameter changes of the connected components.

[0067] Step S242: Perform a threshold judgment on the parameter changes of the connected components to obtain the situation of molten glass flow interruption.

[0068] Exemplarily, detect flow interruption according to the changes of connected component parameters and the time window. When the area changes, judge whether the molten glass is flowing interrupted by the absolute value of the difference between the area of the connected component at the previous moment and the area of the connected component at the next moment. If the area change is greater than the threshold or the centroid change is greater than the threshold, the count value of the flow interruption detection accumulator is incremented by one. When the flow interruption detection accumulator is greater than the number of needles in the time window, it is determined that the molten glass is flowing interrupted.

[0069] After completing the preliminary judgment on whether the molten glass is flowing interrupted, in order to ensure the stability of the production process and the product quality, it is also necessary to detect the width of the molten glass to discover potential problems and take corresponding measures for adjustment to ensure the uniformity and continuity of the molten glass flow, and further improve the production efficiency and product quality.

[0070] In an embodiment of the present application, the process of obtaining the actual width of the molten glass includes the following steps S31 to S33.

[0071] Step S31: Extract edge features from the glass liquid image to obtain the upper-edge pixel points and lower-edge pixel points of the glass liquid.

[0072] Exemplarily, extract the features of the glass liquid edge for each glass liquid image to obtain the upper-edge pixel coordinates and lower-edge pixel coordinates of the glass liquid. Assume that the detected upper-edge pixel point coordinates of the glass liquid are (x1, y1), and the lower-edge pixel point coordinates of the glass liquid are (x2, y2).

[0073] Step S32: Obtain the pixel width of the glass liquid based on the upper-edge pixel points and lower-edge pixel points of the glass liquid.

[0074] Exemplarily, based on the upper-edge pixel point coordinates (x1, y1) and lower-edge pixel point coordinates (x2, y2) of the glass liquid, the pixel width at the pixel level can be obtained. The pixel width d pixel can be expressed as:

[0075]

[0076] Step S33: Perform proportional conversion on the pixel width of the glass liquid to obtain the actual width of the glass liquid.

[0077] Exemplarily, to ensure that the image measurement results have the meaning and accuracy in the real world and the measurement results can be standardized and compared among different systems and devices, it is necessary to convert the pixel width into the actual physical width. During the system debugging phase, place a standard object with a known width at the position where the glass liquid flows through, collect its image, and obtain the pixel width in the image. Let the actual width of the standard object be D real , and its pixel width in the image is d pixel , and the proportional coefficient is k. Then the actual width of the glass liquid can be expressed as:

[0078] k = D real / d pixel

[0079] D = k × d pixel

[0080] In some embodiments, taking the process of obtaining the width of a rectangular glass liquid strip as an example for detailed introduction. It should be noted that the content in this example is only used to explain and illustrate the glass liquid method provided by the embodiments of the present application, rather than to limit the protection scope of the present application in any way. In specific applications, corresponding steps can be added or deleted based on actual needs on the basis of this example. The width measurement process of the rectangular glass liquid strip in this example includes the following steps.

[0081] Step 100: Collect the glass liquid image and extract the edge features of the glass liquid image.

[0082] Step 101: Collect images of molten glass through multiple industrial cameras.

[0083] Step 102: Grayscale and smooth the molten glass images to remove noise in the images.

[0084] Step 103: Extract edge features from the preprocessed images to identify the positions where the gray-scale emphasis changes most significantly in the images, i.e., the edges of the molten glass.

[0085] Step 104: Refine the extracted edge features of the molten glass using the non-maximum suppression algorithm to remove edge noise points.

[0086] Step 105: Further screen the edge features using the double-threshold algorithm. When the pixel intensity exceeds the upper threshold, it is marked as a strong boundary and regarded as the edge of the molten glass. When the pixel intensity is below the lower threshold, it is marked as a weak boundary. Perform edge connection operations on the pixel points of the weak boundary. If it is adjacent to the determined strong boundary pixels, it is determined as a real boundary; otherwise, it is regarded as a non-edge.

[0087] Step 110: Obtain the minimum bounding rectangle of the edge contour and measure the width of the rectangle.

[0088] Step 111: Use the contour detection algorithm to identify and extract the edge pixel points confirmed in Step 105 to obtain the edge contour.

[0089] Step 112: Obtain the minimum bounding rectangle of the detected contour and the corresponding size information of the minimum bounding rectangle. The corresponding size information of the minimum bounding rectangle includes the coordinates (x, y) of the upper left corner of the rectangle, as well as the width (w) and height (h) of the rectangle.

[0090] Step 113: Screen out the rectangle with the largest width from the minimum bounding rectangles in Step 202, and use its width value as the measurement result of the width of the molten glass.

[0091] In an embodiment of the present application, the method for detecting and regulating the breaking of the molten glass plate further includes the following steps S41 to S43.

[0092] Step S41: Calibrate the industrial cameras using the checkerboard calibration method to obtain the internal parameters and external parameters of the multiple industrial cameras.

[0093] Since there are different perspectives and positions in the multi-camera system, the images of the molten glass collected by each camera may have certain deformations and perspective differences. To ensure the consistency of width measurement, it is first necessary to accurately calibrate the multi-cameras. The internal parameters of the industrial cameras are, for example, focal length and principal point coordinates, and the external parameters of the industrial cameras are, for example, rotation and translation vectors.

[0094] Step S42: Convert the glass liquid width data to the world coordinate system using the external parameters.

[0095] Exemplarily, when measuring the width of the glass liquid, the width of the glass liquid obtained from the glass liquid image is converted to the world coordinate system. Suppose in the camera coordinate system, the glass liquid width data point measured by an industrial camera is P local , through the external parameter rotation matrix R and translation vector T obtained by calibration, it is converted to the world coordinate system through the coordinate transformation formula, so that the glass liquid width data measured by different industrial cameras can be uniformly processed and compared in the world coordinate system. Among them, the coordinate transformation formula can be expressed as:

[0096] P world = R × P local + T

[0097] Step S43: Perform weighted fusion processing on the glass liquid width data in multiple consecutive frames of glass liquid images to obtain the global width range of the glass liquid.

[0098] Exemplarily, the width of the glass liquid measured in the i-th frame of the image is D i , and its corresponding weight is w i , and the width of the fused glass liquid is D fused , then D fused The calculation formula can be expressed as:

[0099]

[0100] where n is the number of frames participating in the fusion.

[0101] It should be noted that the weight can be determined according to factors such as image quality and similarity to adjacent frames.

[0102] Due to the slight fluctuations in the flow of the glass liquid, by performing fusion processing such as weighted averaging on the glass liquid width measurement data in multiple consecutive frames of images, the measurement error can be effectively reduced and the accuracy of the glass liquid width detection can be improved.

[0103] After measuring the width of the glass liquid, based on the obtained width measurement data, we need to precisely adjust the opening degree of the gate to ensure that the width of the glass liquid is always within the ideal production standard. The specific adjustment process is as follows:

[0104] a. If the width of the glass liquid is less than the set lower width limit, the opening degree of the gate should be appropriately increased at this time. The new opening degree of the gate will be the current opening degree of the gate plus a preset gate adjustment step size, but it is necessary to ensure that the gate adjustment step size does not exceed the maximum allowable value of the gate opening degree.

[0105] b. If the width of the molten glass is greater than the set upper limit of the width, the opening of the gate plate needs to be reduced accordingly. The new opening of the gate plate will be the current opening of the gate plate minus the adjustment step of the gate plate, and the adjustment step of the gate plate is not less than the minimum value of the opening of the gate plate.

[0106] c. When the width of the molten glass is within the normal range, that is, between the lower limit and the upper limit of the width, it indicates that the current opening of the gate plate is quite appropriate and no adjustment is required, and the existing state can be maintained.

[0107] Next, a specific example will be used to introduce in detail the method for detecting and controlling the broken plate of the molten glass plate provided by the embodiment of the present application. It should be noted that the content in this example is only used to explain and illustrate the method for detecting and controlling the broken plate of the molten glass plate provided by the embodiment of the present application, rather than for any limitation of the protection scope of the present application. In specific applications, corresponding steps can be added or deleted based on actual needs on the basis of this example. Figure 4 Shown is the flow chart of the method for detecting and controlling the broken plate of the molten glass plate in this example. As Figure 4 shown, the method for detecting and controlling the broken plate of the molten glass plate in this example includes the following steps.

[0108] Step 500, detect and analyze the broken plate of the molten glass.

[0109] Step 501, collect images of the broken plate of the molten glass using multiple industrial cameras. Initialize the list of industrial cameras and capture video frames through a loop.

[0110] Step 502, perform image preprocessing on the collected images of the broken plate of the molten glass. Process the images of the broken plate of the molten glass using grayscale conversion, Gaussian blur, and edge detection to obtain the processed images of the broken plate of the molten glass.

[0111] Step 503, perform connected component analysis on the processed images of the broken plate of the molten glass. Obtain the statistical information of the connected components, and screen the area and centroid coordinates of the connected component regions.

[0112] Step 510, adjust the plate width based on the detected broken plate of the molten glass.

[0113] Step 511, obtain the image of the glass plate width, perform edge detection and contour extraction on the image of the glass plate width to obtain the maximum width.

[0114] Step 512, determine whether the width of the molten glass exceeds the limit, and output a response alarm when the width exceeds the limit.

[0115] Step 513, obtain the current opening state of the gate plate, and adjust the step size of the upper and lower limits of the opening based on the current opening of the gate plate.

[0116] In summary, the glass liquid plate breakage detection and regulation method provided by this application can use multiple industrial cameras to monitor the width change of the glass liquid in real time from different angles. By extracting the boundary of the glass liquid from the collected glass liquid images, the actual width of the glass liquid is obtained based on the calibration parameters of the cameras, and the global width range of the glass liquid is obtained through the weighted fusion of the cameras. At the same time, based on the set width threshold, abnormal situations such as over-width or interruption of the glass liquid width are judged. If the width is lower than the set boundary threshold, the opening degree of the regulating gate of the larger flow channel is automatically adjusted by the control mechanism to increase the width of the glass liquid. If the width is higher than the set boundary threshold, the opening degree of the regulating gate of the flow channel is automatically reduced to adjust the width of the glass liquid to a reasonable range, and at the same time, the buzzer and the LED lamp are triggered for audible and visual alarm prompts. The multi-camera inlet plate width automatic control and outlet breakage detection based on Python image processing realize the high-precision monitoring of the glass liquid width, the rapid response to abnormal situations and the automatic adjustment, effectively solve the deficiencies of the traditional detection means in terms of accuracy and real-time performance, and provide a reference for the automated monitoring based on image detection in the glass manufacturing industry and other industrial fields.

[0117] The protection scope of the glass liquid plate breakage detection and regulation method described in the embodiments of this application is not limited to the execution order of the steps listed in this embodiment. Any solution realized by adding or subtracting steps of the prior art and replacing steps according to the principle of this application is included in the protection scope of this application.

[0118] The embodiments of this application also provide a glass liquid plate breakage detection and regulation system. The glass liquid plate breakage detection and regulation system can implement the glass liquid plate breakage detection and regulation method described in this application. However, the implementation devices of the glass liquid plate breakage detection and regulation method described in this application include but are not limited to the structure of the glass liquid plate breakage detection and regulation system listed in this embodiment. Any structural deformation and replacement of the prior art made according to the principle of this application are included in the protection scope of this application.

[0119] Figure 5 It shows a schematic structural diagram of the glass liquid plate breakage detection and regulation system in an embodiment of this application. As Figure 5 shown, the glass liquid plate breakage detection and regulation system 1 includes: a glass liquid image acquisition module 11, a data acquisition module 12, an actual width acquisition module 13, and a judgment and adjustment module 14. Among them, the glass liquid image acquisition module 11 is used to collect continuous glass liquid images by using multiple industrial cameras. The data acquisition module 12 is used to obtain the glass liquid boundary and the glass liquid width data according to the glass liquid images. The actual width acquisition module 13 is used to obtain the actual width of the glass liquid based on the glass liquid boundary and the calibration parameters of the industrial cameras. The judgment and adjustment module 14 is used to judge the width threshold of the actual width of the glass liquid and adjust the opening degree of the regulating gate of the flow channel based on the judgment result.

[0120] It should be noted that Figure 5 each module in the glass liquid plate break detection and regulation system 1 shown corresponds one by one to Figure 2 the steps in the glass liquid plate break detection and regulation method described above, and will not be elaborated here.

[0121] In several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules / units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or modules or units can be in electrical, mechanical or other forms.

[0122] The modules / units described as separate components may or may not be physically separated. The components shown as modules / units may or may not be physical modules, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the modules / units can be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, in each embodiment of the present application, the functional modules / units can be integrated in a processing module, or each module / unit can exist physically alone, or two or more modules / units can be integrated in one module / unit.

[0123] Those of ordinary skill in the art should also be further aware that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0124] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the glass sheet breaking detection and regulation method provided by the embodiments of the present application. Those of ordinary skill in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing a processor through a program. The said program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrating one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid-state disk (SSD)), etc.

[0125] The embodiments of the present application can also provide an electronic device. Figure 6 Shown is a schematic structural diagram of the electronic device 2 in an embodiment of the present application. As Figure 6 shown, the electronic device 2 in this embodiment includes a memory 21 and a processor 22.

[0126] The memory 21 is used to store a computer program. In some possible implementation manners, the memory 21 may include: various media that can store program codes, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disc.

[0127] In the embodiments of the present application, the memory 21 may include a computer system-readable medium in the form of volatile memory, such as RAM and / or cache memory. The electronic device 2 may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 21 may include at least one program product, and the program product has a set (for example, at least one) of program modules, and these program modules are configured to execute the functions of the embodiments of the present application.

[0128] The processor 22 is connected to the memory 21 and is used to execute the computer program stored in the memory 21, so that the electronic device 2 executes the glass sheet breaking detection and regulation method.

[0129] Exemplarily, the processor 22 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. In other embodiments, the processor 22 may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0130] In some implementations, the electronic device 2 provided in the embodiments of the present application may further include a display 23. The display 23 is communicatively connected to the memory 21 and the processor 22, and is configured to display a relevant Graphical User Interface (GUI) of the glass sheet breaking detection and regulation method.

[0131] In the embodiments of the present application, the display 23 may include a display screen (display panel). In some implementations, the display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), etc. In addition, the display 23 may also be a touch panel (touch screen, touch display screen), and the touch panel may include a display screen and a touch-sensitive surface. When the touch-sensitive surface detects a touch operation on or near it, it is transmitted to the processor 22 to determine the type of touch event, and then the processor 22 provides a corresponding visual output on the display device according to the type of touch event.

[0132] The descriptions of the processes or structures corresponding to the above respective drawings each have their own focuses. For parts not detailed in a certain process or structure, reference may be made to the relevant descriptions of other processes or structures.

[0133] The above embodiments merely illustrate the principles and effects of the present application, rather than limiting the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present application should still be covered by the claims of the present application.

Claims

1. A glass liquid plate break detection and control method, characterized in that: The glass liquid plate break detection and control method comprises: Use multiple industrial cameras to collect continuous images of glass liquid; Acquire glass liquid boundary and glass liquid width data according to the glass liquid image; Acquire the actual width of the glass liquid based on the glass liquid boundary and the calibration parameters of the industrial camera; A width threshold is determined for the actual width of the glass liquid, and the opening of the regulating gate of the flow channel is adjusted based on the determination result.

2. The glass liquid plate break detection and control method according to claim 1, characterized in that: The glass liquid plate break detection and control method also includes: Processing the glass liquid image to obtain a glass liquid region; The molten glass region is processed by morphological operation to obtain molten glass enhancement characteristics; Based on the glass liquid enhancement characteristics, a connected domain analysis algorithm is used to obtain a connected domain of the glass liquid region; The parameter changes of the connected domain are judged and analyzed to obtain the glass liquid interruption situation.

3. The glass liquid plate break detection and control method according to claim 2, characterized in that: The process of processing the glass liquid image to obtain the glass liquid area includes: Preprocessing the glass liquid image to obtain a pure glass liquid image; Threshold segmentation is performed on the pure molten glass image to obtain a molten glass region.

4. The glass liquid plate break detection and control method according to claim 2, characterized in that: The process of judging and analyzing the parameter changes of the connected domain to obtain the glass liquid interruption situation includes: Analyzing the connected domains between adjacent image frames to obtain parameter changes of the connected domains; A threshold value is judged on the parameter change of the connected domain to obtain the glass liquid interruption situation.

5. The glass liquid plate break detection and control method according to claim 1, characterized in that: The process of obtaining the actual width of the glass liquid includes: Extracting edge features of the glass liquid image to obtain upper edge pixel points and lower edge pixel points of the glass liquid; Acquire the pixel width of the glass liquid according to the pixel point of the upper edge of the glass liquid and the pixel point of the lower edge of the glass liquid; The pixel width of the glass liquid is proportionally converted to obtain the actual width of the glass liquid.

6. The glass liquid plate break detection and control method according to claim 1, characterized in that: The glass liquid plate break detection and control method also includes: Calibrate the industrial camera using a checkerboard calibration method to obtain internal parameters and external parameters of a plurality of the industrial cameras; The glass liquid width data is converted into a world coordinate system using the external parameters.

7. The glass liquid plate break detection and control method according to claim 1, characterized in that: The glass liquid plate break detection and control method also includes: performing weighted fusion processing on glass liquid width data in multiple consecutive frames of glass liquid images to obtain a global width range of the glass liquid.

8. A glass liquid plate break detection and control system, characterized in that: The glass liquid plate break detection and control system comprises: A glass liquid image acquisition module, used to collect continuous glass liquid images using multiple industrial cameras; A data acquisition module, used for acquiring glass liquid boundary and glass liquid width data according to the glass liquid image; An actual width acquisition module, used to acquire the actual width of the glass liquid based on the glass liquid boundary and the calibration parameters of the industrial camera; The judgment and adjustment module is used to judge the width threshold of the actual width of the glass liquid and adjust the opening of the flow channel regulating gate based on the judgment result.

9. An electronic device, characterized in that: The electronic device comprises: a memory having a computer program stored thereon; A processor is communicatively connected to the memory and is used to execute the computer program to implement the glass liquid plate breakage detection and control method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by an electronic device, the glass liquid plate breakage detection and control method described in any one of claims 1 to 7 is implemented.

Images