Method, device and equipment for calculating melting process of batch in glass kiln

Abstract

The invention relates to the technical field of industrial furnace melting process monitoring and control, in particular to a method, a device and equipment for calculating the melting process of batch in a glass furnace. The method comprises the following steps: S1, acquiring image data of a melting area through an endoscope arranged at the front end of a kiln, and acquiring temperature and infrared emissivity information of corresponding pixel points; s2, processing the image data based on the temperature and infrared emissivity information, and distinguishing a batch area and a melt area to obtain a mask image of the batch area; s3, according to the mask image, calculating the proportion value of the pixel area of the batch area to the total pixel area of the melting area, and taking the proportion value as the overall melting rate; s4, comparing the proportion value with a preset ideal melting rate and an allowable deviation range to obtain a melting state judgment result; and S5, generating a working condition adjustment suggestion or a control instruction according to the melting state judgment result. According to the invention, quantitative evaluation and working condition adjustment of the glass kiln batch melting process are realized.

Description

Technical Field

[0001] This invention relates to the field of industrial furnace melting process monitoring and control technology, and in particular to a method, apparatus and equipment for calculating the melting process of batch materials in a glass furnace. Background Technology

[0002] In the glass production process using flame heating, raw materials are first weighed and mixed according to the formula to prepare a batch. This batch is then fed into the furnace via a feeder, causing it to float on the surface of the molten glass. Under the thrust of the feeder, the batch floating on the surface slowly moves towards the forming zone and gradually melts, with the area covered by the batch above the molten glass gradually decreasing. At the feed inlet area, the batch usually completely covers the molten glass surface. As it moves forward, the ambient temperature gradually increases, causing the batch temperature to rise and continue melting. When the batch reaches the vicinity of the high-temperature hotspots inside the furnace, it will completely melt into a melt containing numerous bubbles, and eventually, the batch will disappear.

[0003] During this process, changes in the operating temperature and the physical properties of the batch materials inside the kiln are directly reflected in observable phenomena within the kiln. These include changes in the position of the material pile, changes in the foam area after the batch materials melt, and changes in the size of the material pile and foam area. These phenomena are important indicators of changes in the melting process; abnormal changes may lead to deterioration of melting quality, thereby affecting product quality. Therefore, timely and accurate observation and analysis of the melting process within the kiln are of great significance for stabilizing the melting operation and improving the quality of the finished product.

[0004] However, current glass production lines generally still rely on manual observation of the position changes of the batch material piles and the farthest point of the foam zone within the furnace to determine the melting state. This operator-dependent control model has the following drawbacks: 1) The melting rate and process of the batch cannot be quantitatively assessed, resulting in fluctuations in the quality of the melting operation and increased energy consumption; 2) Manual observation can only make judgments after the melting results have been displayed, which has a significant lag. When an anomaly occurs, it can only be remedied passively and cannot be prevented in advance. 3) Over-reliance on the experience and condition of operators leads to large fluctuations in the process and poor production stability.

[0005] For example, Chinese patent CN201510255772.X discloses a dynamic feeding control method for glass furnaces. This method uses a liquid level sensor to monitor the glass melt height in real time, dynamically adjusts the feeding speed and gas actuator power based on a preset liquid level threshold, and incorporates external disturbance monitoring for coordinated control. While this technology can reduce manual operation delays and improve feeding accuracy and production stability, its monitoring indicators are concentrated on liquid level changes. It balances the furnace output by increasing or decreasing the amount of batch material fed into the furnace to maintain stable control of the glass melt level. However, it lacks direct and quantitative detection methods for the distribution of the batch material in the melting zone and the melting rate, failing to reflect local changes and overall trends during the melting process.

[0006] Therefore, there is an urgent need for a method and system that can directly identify the distribution of batch materials and quantify the melting rate based on real-time images inside the kiln, in order to overcome the shortcomings of existing technologies that rely on indirect parameters or human experience, and to achieve accurate assessment and effective control of the melting process. Summary of the Invention

[0007] This application aims to address at least one of the technical problems existing in the prior art by providing a method, apparatus, and equipment for calculating the melting process of batch materials in a glass furnace. This method allows for real-time quantitative evaluation of the distribution and melting rate of the batch materials within the furnace's melting zone, yielding results for determining the overall melting state of the batch materials and specific zones. During production, the operating conditions can be judged based on a comparison between the real-time calculated melting rate and a preset ideal rate. Adjustment suggestions or control commands can be output to a distributed control system (DCS) or intelligent control system to achieve manual or automatic adjustment of the burner's heat supply, thereby maintaining the stability of the melting process, reducing energy consumption fluctuations, and improving the consistency of the finished glass quality.

[0008] In a first aspect, embodiments of this application provide a method for calculating the melting process of batch materials in a glass furnace, the method including: S1. Image data of the melting zone is acquired by an endoscope set at the front end of the kiln, and the temperature and infrared emissivity information of the corresponding pixels are obtained; S2. Based on the temperature and infrared emissivity information, the image data is processed to distinguish between the batch material area and the melt area, and a mask image of the batch material area is obtained; S3. Based on the mask image, calculate the ratio of the pixel area of ​​the batch material region to the total pixel area of ​​the melting region, and use it as the overall melting rate; S4. Compare the ratio value with the preset ideal melting rate and allowable deviation range to obtain the melting state determination result; S5. Based on the melting state determination result, generate operating condition adjustment suggestions or control instructions.

[0009] The method for calculating the melting process of batch materials in a glass furnace according to the embodiments of this application has at least the following beneficial effects: The method for calculating the melting process of batch materials in a glass furnace according to this application first acquires real-time images of the melting zone of the furnace using a high-temperature resistant endoscope and obtains the temperature and infrared emissivity information of the corresponding pixels. Then, it uses an image processing method based on dual-threshold segmentation and edge detection to distinguish between the batch material area and the melt area. Next, it calculates the ratio of the batch material area to the total area of ​​the melting zone as the overall and zone-specific melting rates. Finally, it compares the calculation results with preset ideal values ​​and allowable deviation ranges to generate operating condition adjustment suggestions or control commands. By directly recognizing and quantifying the actual image of the melting zone, it achieves real-time and accurate evaluation of the melting process and realizes stable control.

[0010] According to some embodiments of this application, in S2, the temperature range of the unmelted batch is 800–900°C, its emissivity is 0.65–0.75, and the infrared image shows dark patches; the glass temperature at the initial stage of melting is 1200–1250°C, its emissivity is 0.80–0.85, and the infrared image shows a mixture of bright and dark areas with bubble texture; the temperature of the fully molten glass is greater than 1300°C, its emissivity is 0.85–0.92, and the infrared image shows a uniform bright area.

[0011] According to some embodiments of this application, step S2 further includes: performing pseudo-color rendering and grayscale enhancement on the image to enhance the boundary contrast between the batch region and the melt region.

[0012] According to some embodiments of this application, boundary differentiation includes: employing a segmentation method based on temperature threshold and emissivity threshold, combined with an edge detection algorithm; and, under complex working conditions, employing a recognition algorithm based on a deep learning model to identify the boundary between the batch material and the melt.

[0013] According to some embodiments of this application, the endoscope is a retractable structure, equipped with a wide-angle lens and an autofocus assembly, and connected to an uncooled infrared camera with a cooling device.

[0014] According to some embodiments of this application, S1 further includes: collecting temperature data through platinum thermocouple sensors distributed on the inner wall of the furnace and the surface of the molten glass, for use in assisting in determining the melting state.

[0015] According to some embodiments of this application, in S5, the operating condition adjustment command is used for heating regulation, and the heating regulation includes: using a distributed control system (DCS) to adjust the fuel control valve to adjust the fuel supply; and using heating electrodes in the kiln for heating regulation, wherein the heating electrodes include molybdenum electrodes and tin oxide electrodes.

[0016] Secondly, embodiments of this application provide a device for calculating the melting process of batch materials in a glass furnace, the device including: The image acquisition module is used to acquire image data of the melting zone through an endoscope and an infrared camera, and to obtain the temperature and infrared emissivity information of the corresponding pixels; The image processing module is used to perform pseudo-color rendering, grayscale enhancement, and boundary differentiation on the image based on the temperature and infrared emissivity information to obtain a mask image of the batch material area; A rate calculation module is used to calculate the melting rate of the whole and the partitions based on the mask image; The rate comparison module is used to compare the melting rate with a preset ideal melting rate and allowable deviation range to obtain a melting state determination result; The operating condition adjustment module is used to generate operating condition adjustment suggestions or control instructions based on the melting state determination results.

[0017] The glass furnace batch melting process calculation device according to the embodiments of this application has at least the following beneficial effects: The apparatus of this application embodiment acquires images and infrared parameters of the melting zone using an endoscope and an infrared camera through an image acquisition module. The image processing module then performs pseudo-color rendering, grayscale enhancement, and boundary differentiation on the acquired data, accurately distinguishing between the batch material and the melt area. The rate calculation module quickly calculates the overall and zoned melting rates based on the mask image. The rate comparison module compares the actual rate with the ideal rate and allowable deviation range in real time. The operating condition adjustment module generates corresponding adjustment suggestions or control commands. Through the clear division of labor and functional cooperation among the modules, real-time quantitative monitoring and dynamic adjustment of the melting process are achieved, thereby ensuring the stability of the melting process, reducing energy consumption fluctuations, and improving the quality consistency of glass products.

[0018] According to some embodiments of this application, a temperature acquisition module is also included, used to acquire temperature data of the inner wall of the kiln and the surface of the molten glass through a platinum thermocouple sensor; the operating condition adjustment module is used for heating regulation, the heating regulation including: adjusting the fuel control valve through a distributed control system (DCS) to adjust the fuel supply; and driving the heating electrodes through an electrode control unit to perform heating regulation, the heating electrodes including a molybdenum electrode and a tin oxide electrode.

[0019] Thirdly, embodiments of this application also provide a computer device, characterized in that it includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any one of claims 1 to 7.

[0020] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing this application. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the steps of a method for calculating the melting process of batch materials in a glass furnace according to Embodiment 1 of this application. Figure 2 This is a schematic diagram of the internal batching and timely distribution of materials in a glass furnace according to Embodiment 2 of this application; Figure 3 This is a schematic diagram of the internal partitioning of the kiln in Embodiment 2 of this application; Figure 4 This is a diagram showing the correspondence between the kiln zoning and the infrared distribution of the batch material in Embodiment 2 of this application; Figure 5 This is a schematic diagram of the structure of a glass furnace batch melting process calculation device according to Embodiment 3 of this application. Detailed Implementation

[0022] The present application will now be described in further detail with reference to experimental examples and specific embodiments. However, this should not be construed as limiting the scope of the subject matter of the present application to the following embodiments. All technologies implemented based on the content of the present application fall within the scope of protection of the present application.

[0023] Unless otherwise specified, the terms "upper," "lower," "left," "right," "center," "inner," "outer," and "side" used in the description of specific embodiments of this application to indicate orientation or positional relationships are based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is usually placed during use. These terms are merely for the purpose of facilitating the description of the solution in this application or simplifying the description in specific embodiments, so as to enable those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on this application.

[0024] In the description of the embodiments of this application, technical terms such as "first" and "second" only distinguish one entity or operation from another, and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary or secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0025] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] Example 1 During the research process, the applicant discovered that when judging the melting state by manually observing the position of the batch material pile and changes in the foam area within the kiln, obtaining information on the melting rate and progress of the batch material to achieve real-time quantitative evaluation of the melting process requires cumbersome and delayed steps, such as relying on the subjective judgment of operators and long-term manual monitoring. Adjustments to the operating conditions can only be made passively after the melting results have been observed. In solving practical engineering problems, existing technologies cannot meet the need to directly obtain the distribution and melting rate of the batch material in the melting zone in order to achieve real-time and accurate evaluation of the melting process and timely adjustment of heating.

[0027] Therefore, after studying this problem, the applicant proposed a method for calculating the melting process of batch materials in a glass furnace. In response to the problem of unquantifiable and highly lagging melting state monitoring technology, the method uses a high-temperature resistant endoscope at the front end of the furnace to obtain images of the melting zone, and uses the differences in infrared characteristics to identify the batch material area, calculate the overall and zone melting rates and compare them with ideal values. This technical solution realizes real-time quantitative evaluation and adjustment of the melting process, thereby achieving the technical effects of improving the stability of the melting process, reducing energy consumption fluctuations and improving the consistency of finished product quality.

[0028] Please refer to Figure 1 , Figure 1 A schematic diagram illustrating the steps of the method for calculating the melting process of batch materials in a glass furnace provided in this application embodiment. The method for calculating the melting process of batch materials in a glass furnace may include: S1. Image data of the melting zone is acquired by an endoscope set at the front end of the kiln, and the temperature and infrared emissivity information of the corresponding pixels are obtained; S2. Based on the temperature and infrared emissivity information, the image data is processed to distinguish between the batch material area and the melt area, and a mask image of the batch material area is obtained; S3. Based on the mask image, calculate the ratio of the pixel area of ​​the batch material region to the total pixel area of ​​the melting region, and use it as the overall melting rate; S4. Compare the ratio value with the preset ideal melting rate and allowable deviation range to obtain the melting state determination result; S5. Based on the melting state determination result, generate operating condition adjustment suggestions or control instructions.

[0029] The method for calculating the melting process of batch materials in a glass furnace according to the embodiments of this application has at least the following beneficial effects: The method for calculating the melting process of batch materials in a glass furnace according to this application first acquires real-time images of the melting zone of the furnace using a high-temperature resistant endoscope and obtains the temperature and infrared emissivity information of the corresponding pixels. Then, it uses an image processing method based on dual-threshold segmentation and edge detection to distinguish between the batch material area and the melt area. Next, it calculates the ratio of the batch material area to the total area of ​​the melting zone as the overall and zone-specific melting rates. Finally, it compares the calculation results with preset ideal values ​​and allowable deviation ranges to generate operating condition adjustment suggestions or control commands. By directly recognizing and quantifying the actual image of the melting zone, it achieves real-time and accurate evaluation of the melting process and realizes stable control.

[0030] According to some embodiments of this application, in S2, the temperature range of the unmelted batch is 800–900°C, its emissivity is 0.65–0.75, and the infrared image shows dark patches; the glass temperature at the initial stage of melting is 1200–1250°C, its emissivity is 0.80–0.85, and the infrared image shows a mixture of bright and dark areas with bubble texture; the temperature of the fully molten glass is greater than 1300°C, its emissivity is 0.85–0.92, and the infrared image shows a uniform bright area.

[0031] According to some embodiments of this application, step S2 further includes: performing pseudo-color rendering and grayscale enhancement on the image to enhance the boundary contrast between the batch region and the melt region.

[0032] According to some embodiments of this application, boundary differentiation includes: employing a segmentation method based on temperature threshold and emissivity threshold, combined with an edge detection algorithm; and, under complex working conditions, employing a recognition algorithm based on a deep learning model to identify the boundary between the batch material and the melt.

[0033] According to some embodiments of this application, the endoscope is a retractable structure, equipped with a wide-angle lens and an autofocus assembly, and connected to an uncooled infrared camera with a cooling device.

[0034] According to some embodiments of this application, S1 further includes: collecting temperature data through platinum thermocouple sensors distributed on the inner wall of the furnace and the surface of the molten glass, for use in assisting in determining the melting state.

[0035] According to some embodiments of this application, in S5, the operating condition adjustment command is used for heating regulation, and the heating regulation includes: using a distributed control system (DCS) to adjust the fuel control valve to adjust the fuel supply; and using heating electrodes in the kiln for heating regulation, wherein the heating electrodes include molybdenum electrodes and tin oxide electrodes.

[0036] The method for calculating and controlling the melting process of batch materials in a glass furnace provided in this application embodiment can be applied to many technical fields, such as monitoring and controlling high-temperature industrial melting processes, including glass manufacturing and metal smelting. In the above implementation, when controlling the melting process, images of the melting zone can be acquired using a high-temperature resistant endoscope. Infrared characteristic analysis and image processing technology can be used to identify the batch material area and calculate the melting rate. By comparing the real-time calculation results with preset ideal values ​​and allowable deviation ranges, the overall and zoned melting rates can be determined, thereby achieving the effects of timely adjustment of heating, maintaining a stable melting process, reducing energy consumption fluctuations, and improving product quality consistency.

[0037] Example 2 As a further optimization of the preceding embodiments, this application provides a specific implementation method for calculating the melting process of batch materials in a glass furnace. Based on the differences in infrared characteristics such as temperature and emissivity between the batch materials and the melt, the boundary between the batch materials and the high-temperature melt is distinguished and marked, thus differentiating the batch materials from the melt. An algorithm model is used to calculate the ratio R (which can be called the melting rate) between the area of ​​the batch materials and the corresponding area of ​​the furnace, thereby determining the melting speed of the batch materials. The specific details are as follows: To eliminate the various defects of existing control modes, this invention installs a high-temperature resistant industrial endoscope at the front end of the kiln (feeding port area), with the lens facing the batching area on the surface of the molten glass. For example... Figure 2 and Figure 3 As shown, where, Figure 2 This is a schematic diagram showing the zoning and timely distribution of the batching material inside the kiln. Figure 3 This is a schematic diagram of the internal partitions of the kiln. The endoscope is installed at the observation hole on the front wall of the kiln through a protective sleeve with dustproof and heat radiation protection. The horizontal distance between the installation position and the batch material is preferably [1, 3] meters. The top viewing angle of the endoscope is [45°, 90°], which can cover the main melting area and reduce the direct impact of high temperature radiation on the lens. A wide-angle lens is preferred to ensure that the observation range covers the entire melting area.

[0038] The endoscope is equipped with an infrared imaging module, or can be used in conjunction with an external infrared temperature measurement device, to acquire the temperature value and infrared emissivity information of the corresponding pixels while acquiring images. During the melting process of glass batches, there is a significant temperature gradient and difference in emissivity between the unmelted solid material and the molten glass. This difference can be captured and quantified using infrared thermal imaging technology.

[0039] Unmelted batch: In the silicate formation stage (800–900°C), mainly composed of solid particles such as polycrystalline salts and quartz sand, with a rough surface and many pores, and low emissivity. ε ≈ 0.6–0.75). The actual temperature is lower than the melt temperature.

[0040] The formed melt: During the glass-forming stage (temperature > 1200°C), the molten glass has a smooth surface and contains bubbles, resulting in high emissivity. ε (≈ 0.85–0.92). The temperature distribution is relatively uniform, and the radiation intensity is higher than that of solid particulate matter.

[0041] Table 1 Temperature range, emissivity, and infrared image performance at different melting stages

[0042] As shown in Table 1, Table 1 presents the temperature range, emissivity, and infrared image representation at different melting stages. Based on the differences in material temperature and emissivity, an infrared detector is first used to receive the infrared thermal radiation signal emitted by the object, converting the radiation intensity into an electrical signal. Then, the infrared detector outputs the original grayscale value, which is mapped to temperature using a radiometric calibration formula. Finally, image contrast enhancement processing is performed. Figure 4 As shown, due to the difference in emissivity between unmelted material and melt, the melt area appears brighter (higher grayscale value) in the infrared image at the same temperature, while the batch material area is darker (lower grayscale value). The boundary between the two can be intuitively distinguished by pseudo-color rendering, the area of ​​unmelted batch material can be calculated, and then the melting rate can be calculated.

[0043] The image processing procedure includes: first, preprocessing the original images acquired by the endoscope, such as denoising, brightness equalization, and distortion correction, to improve the accuracy of subsequent recognition; then, using an image segmentation algorithm based on temperature and grayscale dual thresholds, identifying low-temperature, high-emissivity regions as batch materials and high-temperature, low-emissivity regions as melts; further, marking the batch material boundaries through an edge detection algorithm and generating pixel masks for the batch material regions.

[0044] Based on the recognition results, the ratio R between the area of ​​the batch material inside the kiln and the total area of ​​the kiln is calculated. The area of ​​the batch material is obtained by counting the number of pixels in the mask, and the total area of ​​the kiln is the number of pixels corresponding to the surface of the furnace in the image. This ratio R can be called the melting rate, which reflects the remaining coverage area of ​​the current batch material.

[0045] Based on this, a quantitative rule for melting rate is established. The ideal melting rate is obtained through statistical analysis of historical image data during a normal production cycle. And set the allowable deviation range. (For example, ±5% to ±10%). When the R value is in ± When R varies within a certain range, the melting process is considered normal and no adjustment of the operating conditions is required; when R < - When R > 0, it indicates that the melting rate is too fast and the kiln is providing too much heat; the burner heating should be reduced through the control system. + When the melting rate is too slow, the furnace is not heating enough, and the heat output should be increased.

[0046] The embodiments of this application can display the R value in real time on the DCS system, intelligent control platform or operating terminal, so that the process parameters can be manually monitored and adjusted, or the combustion conditions can be automatically adjusted by the control logic, so as to realize the real-time closed-loop regulation of the melting speed, thereby maintaining the stability of the melting process and improving the consistency of product quality.

[0047] To more accurately quantify and evaluate the melting rate of the batch material at different locations inside the kiln, this invention divides the kiln melting zone along the length of the furnace into multiple equidistant sub-regions, such as A, B, C, D, etc. The number of sub-regions can be determined based on the furnace length and the endoscopic field of view, generally 3 to 6 sub-regions. The range of each sub-region is preset in the endoscopic processor, and its position is mapped through an image coordinate system so that each pixel in the acquired image corresponds to a specific sub-region number.

[0048] When calculating the melting rate of each partition, the processor first performs boundary recognition and pixel area calculation independently for the image region of each partition to obtain the pixel area of ​​the batch material in that partition. , , And the pixel area of ​​the total kiln surface in that zone. , , Wait, then follow the formula:

[0049]

[0050]

[0051] ... The actual melting rate of each zone was calculated separately.

[0052] During system initialization, statistical analysis of historical normal production data will be used to obtain the ideal melting rate value for each partition. , , And so on, and set the allowable deviation range for each partition. , , In actual operation, the processor will calculate the results in real time. , , Compare them with their respective ideal values: When the melting rate value of a certain partition changes within the range of the ideal value ± allowable deviation, the melting state of that partition is considered normal. When the rate value of a certain zone is lower than the ideal value minus the allowable deviation, it indicates that the melting speed of that zone is too fast, and there may be local overheating. The heating supply to that area should be appropriately reduced. When the melting rate value of a certain zone is higher than the ideal value plus the allowable deviation, it indicates that the melting speed of that zone is too slow, and there may be insufficient local heating. The heating in that area should be increased appropriately.

[0053] The application methods for the melting rate R and the rates of each zone can be flexibly selected according to the configuration of the production line's control system: Manual monitoring mode, including R and , , The real-time values ​​of such values ​​are displayed on the DCS system, intelligent control platform, or independent operation panel, allowing operators to manually adjust the burner's firepower or airflow distribution based on the displayed data. In automatic adjustment mode, the R and rate data of each zone are directly input into the control logic of the DCS system. The system then automatically adjusts the heat output of the burners in the corresponding zones according to the set adjustment strategy to achieve closed-loop control of the melting speed. In intelligent control mode, data is transmitted to the intelligent control system, which makes judgments based on historical trends, production plans, and energy consumption targets, and generates optimized control commands to be sent to the DCS system for execution.

[0054] Through this zoned melting rate monitoring and control mechanism, the present invention can not only monitor the overall melting process, but also identify and correct abnormal melting conditions in local areas, thereby further improving the uniformity and stability of the melting operation, reducing energy consumption fluctuations and ensuring product quality consistency.

[0055] Example 3 As a further optimization of the preceding embodiments, this embodiment provides a device for calculating the melting process of batch materials in a glass furnace, such as... Figure 5 As shown, it includes: Image acquisition module: Located at the front end of the kiln, it observes the melting zone through a retractable endoscope and an uncooled infrared camera, acquiring visible light and infrared images and obtaining temperature and infrared emissivity information of the corresponding pixels; the endoscope is equipped with a wide-angle lens and an autofocus component to ensure coverage of the entire melting zone.

[0056] Image processing module: Denoises, equalizes brightness and corrects distortion in the original image, and performs pseudo-color rendering and grayscale enhancement to improve the contrast of the batch and melt boundaries; under complex working conditions, it can also call a boundary recognition algorithm based on deep learning.

[0057] Rate calculation module: Based on the mask image generated by the image processing module, the pixel area of ​​the batching area and the total area of ​​the melting zone are counted respectively, the overall melting rate is calculated, and the melting rate of each zone is further calculated in the furnace length direction or in multi-zone mode.

[0058] Rate comparison module: Compares the overall and zone melting rates with the stored ideal values ​​and tolerance ranges in real time to generate melting status determination results.

[0059] Operating condition adjustment module: Generates adjustment instructions based on the judgment results for operating condition adjustment. These instructions can be sent to the DCS system, intelligent control system, or operation panel to adjust the fuel supply by manually prompting or automatically controlling the fuel control valve. This module can also drive the heating electrode (molybdenum electrode or tin oxide electrode) through the electrode control unit to achieve heat supply adjustment.

[0060] Through the combination and interaction of the above modules, real-time monitoring, quantitative evaluation, and closed-loop control of the melting process are achieved. The modules of this embodiment can be implemented as hardware circuits, embedded systems, or software programs. These modules can be integrated within the same processing unit or distributed across multiple processing units, exchanging data via communication interfaces.

[0061] Example 4 This embodiment provides a device for calculating the melting process of batch materials in a glass furnace, including a memory, a processor, an image acquisition unit, a communication interface, and a high-temperature resistant endoscope installed at the front end of the furnace.

[0062] The memory stores a computer program that can run on a processor, and the processor performs the following functions when executing the program: The image acquisition unit controls the endoscope and infrared camera to acquire visible light and infrared images of the melting zone. Extract temperature and infrared emissivity information from the image, and perform image denoising, brightness equalization, distortion correction, pseudo-color rendering, and boundary recognition. Generate a batch area mask, calculate the overall and zoned melting rates, and compare them with the ideal values ​​and allowable deviation ranges in the memory to determine the melting state. The melting rate results and operating condition adjustment instructions are output to the DCS system, intelligent control system or display terminal through the communication interface for manual intervention or automatic adjustment.

[0063] This equipment can be designed as an integrated industrial testing enclosure, incorporating data acquisition, processing, display, and control interfaces, making it suitable for long-term stable operation in glass kiln production environments.

[0064] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0065] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0066] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for calculating the melting process of batch materials in a glass furnace, characterized in that, include: S1. Image data of the melting zone is acquired by an endoscope set at the front end of the kiln, and the temperature and infrared emissivity information of the corresponding pixels are obtained; S2. Based on the temperature and infrared emissivity information, the image data is processed to distinguish between the batch material area and the melt area, and a mask image of the batch material area is obtained; S3. Based on the mask image, calculate the ratio of the pixel area of ​​the batch material region to the total pixel area of ​​the melting region, and use it as the overall melting rate; S4. Compare the ratio value with the preset ideal melting rate and allowable deviation range to obtain the melting state determination result; S5. Based on the melting state determination result, generate operating condition adjustment suggestions or control instructions.

2. The method according to claim 1, characterized in that, In S2, the temperature range of the unmelted batch is 800–900℃, and its emissivity is 0.65–0.75, appearing as dark patches in the infrared image; the glass temperature in the initial melting stage is 1200–1250℃, and its emissivity is 0.80–0.85, appearing as a mixture of bright and dark areas with bubble texture in the infrared image; the temperature of the fully molten glass is greater than 1300℃, and its emissivity is 0.85–0.92, appearing as a uniform bright area in the infrared image.

3. The method according to claim 1, characterized in that, S2 further includes: performing pseudo-color rendering and grayscale enhancement on the image to enhance the boundary contrast between the batching area and the melt area.

4. The method according to claim 1, characterized in that, Boundary differentiation includes: using a segmentation method based on temperature and emissivity thresholds, combined with an edge detection algorithm; and in complex working conditions, using a recognition algorithm based on a deep learning model to identify the boundary between the batch material and the melt.

5. The method according to claim 1, characterized in that, The endoscope is a retractable structure, equipped with a wide-angle lens and an autofocus component, and connected to an uncooled infrared camera with a cooling device.

6. The method according to claim 1, characterized in that, S1 further includes: collecting temperature data through platinum thermocouple sensors distributed on the inner wall of the kiln and the surface of the molten glass, which is used to assist in judging the melting state.

7. The method according to claim 1, characterized in that, In S5, the operating condition adjustment command is used for heating regulation, which includes: using a distributed control system (DCS) to adjust the fuel control valve to adjust the fuel supply; and using heating electrodes in the kiln for heating regulation, wherein the heating electrodes include molybdenum electrodes and tin oxide electrodes.

8. A device for calculating the melting process of batch materials in a glass furnace, characterized in that, include: The image acquisition module is used to acquire image data of the melting zone through an endoscope and an infrared camera, and to obtain the temperature and infrared emissivity information of the corresponding pixels; The image processing module is used to perform pseudo-color rendering, grayscale enhancement, and boundary differentiation on the image based on the temperature and infrared emissivity information to obtain a mask image of the batch material area; A rate calculation module is used to calculate the melting rate of the whole and the partitions based on the mask image; The rate comparison module is used to compare the melting rate with a preset ideal melting rate and allowable deviation range to obtain a melting state determination result; The operating condition adjustment module is used to generate operating condition adjustment suggestions or control instructions based on the melting state determination results.

9. The apparatus according to claim 8, characterized in that, It also includes a temperature acquisition module, which is used to acquire temperature data of the inner wall of the kiln and the surface of the molten glass through a platinum thermocouple sensor; The operating condition adjustment module is used for heating regulation, which includes: adjusting the fuel control valve through the distributed control system (DCS) to adjust the fuel supply; and driving the heating electrodes through the electrode control unit to perform heating regulation, wherein the heating electrodes include molybdenum electrodes and tin oxide electrodes.

10. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method according to any one of claims 1 to 7.

Images