System and method for monitoring breakage of furnace tube in heating furnace and storage medium
Through visible light imaging technology, the combustion area and flame brightness of the furnace tube are calculated, and the accuracy and cost of the furnace tube rupture monitoring in the prior art are solved, and the accurate monitoring of the furnace tube rupture status is achieved, which ensures the heating furnace safe production.
Patent Information
- Application Number
- CN202310833233.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-07
- Publication Date
- 2025-01-07
AI Technical Summary
When monitoring the rupture of the heating furnace tube, the prior art relies on infrared cameras and thermocouples, which are costly and prone to damage and drift, making it difficult to achieve accurate and timely monitoring, resulting in an increase in the risk of burning and explosion accidents.
Visible light imaging technology is adopted, through the historical image collection module and the real-time image acquisition module, the normal and real-time combustion area area and flame brightness of the furnace tube are calculated respectively, and the evaluation results are generated to judge the fracture state, so as to achieve accurate monitoring of the fracture state of the furnace tube.
Overcome the high cost and easy damage problems of infrared cameras and thermocouples, realize accurate monitoring of the rupture status of the furnace tube, ensure the safe production of the heating furnace, and reduce the risk of burning and explosion accidents.
Smart Images
Figure CN119268378A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of clean and efficient production and explosion safety prevention and control in petrochemical industry, and in particular, relates to a system, method and storage medium for monitoring furnace tube rupture in a heating furnace. Background Art
[0002] The Ministry of Emergency Management's "Catalogue of Outdated Dangerous Chemicals Production Safety Technology and Equipment (First Batch)" clearly points out the risk of explosion in petrochemical heating furnaces, and that adding monitoring modules to heating furnaces is a necessary condition for ensuring safety. Furnace tube rupture is one of the important factors leading to heating furnace explosion accidents. Existing furnace tube monitoring methods mostly rely on infrared cameras or thermocouples, among which infrared cameras are relatively expensive and thermocouples are prone to damage and drift.
[0003] In the process of realizing the present invention, the inventors discovered that the prior art provides a furnace tube image processing method belonging to the field of online monitoring technology. When identifying the monitoring image, this method shields or removes areas that are easily misidentified, thereby greatly improving the accuracy of furnace tube identification; removing the edges of the furnace tube image area to reduce its impact on the analysis results can improve the accuracy of the analysis results and avoid false alarms or omissions of abnormal temperature changes in the furnace tube.
[0004] The prior art also provides a furnace tube temperature monitoring method belonging to the field of online monitoring technology. The method calculates the temperature rise index of the furnace tube based on the monitoring image. The monitoring system can identify the temperature rise of the furnace tube based on the template image analysis, thereby accurately and timely warning of abnormal temperature rise of the furnace tube, so that the operating personnel can deal with the abnormal situation in time to ensure production safety and production continuity.
[0005] In addition, the prior art also provides an integrity management system and method for furnace tubes of a heating furnace. The system stores basic data of furnace tubes through a furnace tube basic data storage and management module, generates a visual furnace tube arrangement diagram, and performs data query, editing and modification on the furnace tubes; stores and manages historical detection and monitoring data of furnace tubes through a furnace tube detection and monitoring result recording and management module; evaluates the damage status, safety status and remaining life of the furnace tubes according to the basic data of the furnace tubes, historical detection data and historical monitoring data through a furnace tube safety life assessment module, and issues early warnings for furnace tubes with excessive damage status, abnormal safety status or insufficient remaining life; sets safe boundaries for process operation temperature parameters for furnace tubes through a furnace tube process integrity operation module, and issues early warnings for furnace tubes with metal wall temperature monitoring values exceeding the safe boundaries. The system can visually manage the full life cycle data of the furnace tubes in the heating furnace, dynamically grasp various status information of the furnace tubes, and improve the management level of the full life cycle of the furnace tubes. Summary of the invention
[0006] In order to solve the above problems, an embodiment of the present invention provides a system for monitoring the rupture of furnace tubes in a heating furnace, comprising: a historical image collection module, which is used to collect historical combustion images of the heating furnace to be monitored when the furnace tubes are not ruptured, so as to determine the normal combustion area in each historical image, and calculate the area and flame brightness of the normal combustion area, based on which, a first threshold for evaluating whether the furnace tube has reached a rupture state according to the area and a second threshold for evaluating whether the furnace tube has reached a rupture state according to the flame brightness are respectively obtained; a real-time image acquisition module, which is used to acquire real-time combustion images of the heating furnace to be monitored, so as to determine the real-time combustion area in each real-time image, and calculate a first parameter and a second parameter of the current combustion area area and the current flame brightness, respectively, the first / second parameters are used to represent parameters for evaluating the degree of the rupture state according to the current combustion area area / current flame brightness; an evaluation result generation module, which is used to obtain an evaluation result of the current furnace tube rupture state by comparing the real-time combustion area with the normal combustion area, the first parameter with the first threshold, and the second parameter with the second threshold.
[0007] Preferably, the arrangement position of the system in the heating furnace to be monitored satisfies the following conditions at the same time:
[0008]
[0009] L monitor ≥ 0.6 L vis
[0010] Among them, L monitor represents the height of the real-time image acquisition module in the heating furnace, R represents the inner diameter of the heating furnace, R1 represents the radius of the furnace nozzle in the heating furnace, and L vis represents the fire height, θ represents the field of view of the real-time image acquisition module, and θ1 represents the depression angle of the real-time image acquisition module.
[0011] Preferably, the historical image collection module is also used to extract the RGB values of the historical combustion images, and analyze the brightness difference between each pixel and all the pixels adjacent to the pixel for each historical combustion image, so that when the brightness of the current pixel is higher than that of all the corresponding pixels, the Boolean variable at the position of the current pixel is activated, and finally the Boolean variable of each historical combustion image is obtained to determine the normal combustion area, the first threshold and the second threshold.
[0012] Preferably, the historical image collection module is also used to train a preset model using a training data set in the historical combustion image to obtain a recognition model for identifying the normal combustion area, the first threshold and the second threshold, thereby using the recognition model to extract the normal combustion area, the first threshold and the second threshold in the test data set in the historical combustion image, and then correct the normal combustion area, the first threshold and the second threshold determined based on the Boolean variables according to the currently extracted prediction results.
[0013] Preferably, the historical image collection module is further used to periodically collect real-time combustion images for which rupture status evaluation has been completed and use them as the historical combustion images to update the recognition model.
[0014] Preferably, the real-time image acquisition module includes: a first acquisition unit, which is used to extract the RGB value of the real-time image, based on which, for each real-time image, the brightness difference between each pixel and all the pixels adjacent to the pixel is analyzed, so that when the brightness of the current pixel is higher than that of all the corresponding pixels, the Boolean variable at the position of the current pixel is activated to obtain the Boolean variable of each real-time image to determine the first type of real-time combustion area, the first type of first parameter and the first type of second parameter related to the brightness difference; a second acquisition unit, which is used to extract the RGB value of the real-time image and analyze the brightness of each pixel for each real-time image. Gradient, so that when the brightness gradient of the pixel point is greater than zero, the Boolean variable at the position of the current pixel point is activated to obtain the Boolean variable of each real-time image to determine the second type of real-time combustion area, the second type of first parameter and the second type of second parameter related to the brightness gradient; a parameter correction unit, which is used to analyze and compare the first type of real-time combustion area with the second type of real-time combustion area, the first type of first parameter with the second type of first parameter, and the first type of second parameter with the second type of second parameter, respectively, to obtain the best real-time combustion area, the best first parameter and the best second parameter for evaluating the actual rupture state of the current furnace tube, and output them.
[0015] Preferably, the evaluation result generation module includes: an analysis unit, which is used to determine whether there is an overlap between the normal combustion area and the real-time combustion area, wherein when there is no overlap, it is determined that the current furnace tube is in a ruptured state, and when there is an overlap, it is also diagnosed whether the current furnace tube is in a ruptured state by judging the size relationship between the first parameter and the first threshold, and the size relationship between the second parameter and the second threshold, wherein if the first parameter is greater than the first threshold and the second parameter is less than the second threshold, it is determined that the current furnace tube is in a ruptured state; if the first parameter is less than the first threshold and the second parameter is greater than the second threshold, it is determined that the current furnace tube is in a ruptured state; if the first parameter is greater than the first threshold and the second parameter is greater than the second threshold, it is determined that the current furnace tube is in a ruptured state; if the first parameter is greater than the first threshold and the second parameter is greater than the second threshold, it is determined that the current furnace tube is in a ruptured state.
[0016] Preferably, the system further comprises: an alarm module, which is used for, when determining that the furnace tube is in a ruptured state, to alarm for the current ruptured state, and to generate a first alarm message for alarming for a ruptured state when there is no overlap phenomenon, or to generate a second alarm message for alarming for a ruptured state when there is an overlap phenomenon.
[0017] Preferably, the system has a temperature tolerance greater than or equal to 1500°C.
[0018] Preferably, the flame brightness of the normal combustion area is the average brightness of each pixel point in the corresponding combustion area, and the flame brightness of the real-time combustion area is the average brightness of each pixel point in the corresponding combustion area.
[0019] In a second aspect, the present invention also provides a method for monitoring the rupture of furnace tubes in a heating furnace, the method being implemented using a system for monitoring the rupture of furnace tubes in a heating furnace, wherein the method comprises: using a historical image collection module to collect historical combustion images of the heating furnace to be monitored when the furnace tubes are not ruptured, thereby determining the normal combustion area in each historical image, and calculating the area and flame brightness of the normal combustion area, based on which, respectively obtaining a first threshold for evaluating whether the furnace tube has reached a rupture state based on the area and a second threshold for evaluating whether the furnace tube has reached a rupture state based on the flame brightness; using a real-time image acquisition module to acquire real-time combustion images of the heating furnace to be monitored, thereby determining the real-time combustion area in each real-time image, and respectively calculating a first parameter and a second parameter of the current combustion area area and the current flame brightness, the first / second parameters being used to represent parameters for evaluating the degree of the rupture state based on the current combustion area area / current flame brightness; an evaluation result generation module obtains an evaluation result of the current furnace tube rupture state by respectively comparing the real-time combustion area with the normal combustion area, the first parameter with the first threshold, and the second parameter with the second threshold.
[0020] Preferably, in the step of using the historical image collection module to collect historical combustion images of the heating furnace to be monitored when the furnace tube is not broken, thereby determining the normal combustion area in each historical image, and calculating the area and flame brightness of the normal combustion area, it includes: using the historical image collection module to extract the RGB value of the historical combustion image, and analyzing the brightness difference between each pixel point and all pixel points adjacent to the pixel point for each historical combustion image, so that when the brightness of the current pixel point is higher than that of all corresponding pixel points, the Boolean variable at the position of the current pixel point is activated, and finally the Boolean variable of each historical combustion image is obtained to determine the normal combustion area, the first threshold value and the second threshold value.
[0021] In a third aspect, the present invention further provides a computer-readable storage medium for executing a series of instructions of the method steps for monitoring the rupture of furnace tubes in a heating furnace.
[0022] Compared with the prior art, one or more embodiments of the above scheme may have the following advantages or beneficial effects:
[0023] The present invention proposes a system, method and storage medium for monitoring the rupture of furnace tubes in a heating furnace. The historical image collection module of the system obtains the normal combustion area of the furnace fire in the heating furnace from the historical combustion image, and respectively calculates the thresholds for evaluating whether the furnace tube has reached the rupture state according to the area and flame brightness; the real-time image acquisition module shoots the real-time combustion image in the heating furnace based on visible light imaging, determines the real-time combustion area of the furnace fire in the heating furnace, and respectively calculates the parameters representing the evaluation of the degree of rupture according to the current combustion area area and the current flame brightness; the evaluation result generation module obtains the evaluation result of the current furnace tube rupture state by comparing the real-time combustion area with the normal combustion area, as well as the parameters and the threshold. The present invention adopts the visible light imaging method to realize the accurate monitoring of the furnace tube rupture state and ensure the safe production of the heating furnace.
[0024] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0026] Figure 1It is a schematic diagram of the overall structure of a system for monitoring furnace tube rupture in a heating furnace according to an embodiment of the present application.
[0027] Figure 2 It is a step diagram of a method for monitoring furnace tube rupture in a heating furnace according to an embodiment of the present application. DETAILED DESCRIPTION
[0028] The following will describe the implementation methods of the present invention in detail with reference to the accompanying drawings and embodiments, so that the implementation process of how the present invention applies technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. It should be noted that as long as there is no conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.
[0029] In addition, the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be performed in an order different from that shown here.
[0030] The Ministry of Emergency Management's "Catalogue of Outdated Dangerous Chemicals Production Safety Technology and Equipment (First Batch)" clearly points out the risk of explosion in petrochemical heating furnaces, and that adding monitoring modules to heating furnaces is a necessary condition for ensuring safety. Furnace tube rupture is one of the important factors leading to heating furnace explosion accidents. Existing furnace tube monitoring methods mostly rely on infrared cameras or thermocouples, among which infrared cameras are relatively expensive and thermocouples are prone to damage and drift.
[0031] In the process of realizing the present invention, the inventors discovered that the prior art provides a furnace tube image processing method belonging to the field of online monitoring technology. When identifying the monitoring image, this method shields or removes areas that are easily misidentified, thereby greatly improving the accuracy of furnace tube identification; removing the edges of the furnace tube image area to reduce its impact on the analysis results can improve the accuracy of the analysis results and avoid false alarms or omissions of abnormal temperature changes in the furnace tube.
[0032] The prior art also provides a furnace tube temperature monitoring method belonging to the field of online monitoring technology. The method calculates the temperature rise index of the furnace tube based on the monitoring image. The monitoring system can identify the temperature rise of the furnace tube based on the template image analysis, thereby accurately and timely warning of abnormal temperature rise of the furnace tube, so that the operating personnel can deal with the abnormal situation in time to ensure production safety and production continuity.
[0033] In addition, the prior art also provides an integrity management system and method for furnace tubes of a heating furnace. The system stores basic data of furnace tubes through a furnace tube basic data storage and management module, generates a visual furnace tube arrangement diagram, and performs data query, editing and modification on the furnace tubes; stores and manages historical detection and monitoring data of furnace tubes through a furnace tube detection and monitoring result recording and management module; evaluates the damage status, safety status and remaining life of the furnace tubes according to the basic data of the furnace tubes, historical detection data and historical monitoring data through a furnace tube safety life assessment module, and issues early warnings for furnace tubes with excessive damage status, abnormal safety status or insufficient remaining life; sets safe boundaries for process operation temperature parameters for furnace tubes through a furnace tube process integrity operation module, and issues early warnings for furnace tubes with metal wall temperature monitoring values exceeding the safe boundaries. The system can visually manage the full life cycle data of the furnace tubes in the heating furnace, dynamically grasp various status information of the furnace tubes, and improve the management level of the full life cycle of the furnace tubes.
[0034] In order to solve the above problems, the present invention proposes a system, method and storage medium for monitoring the rupture of furnace tubes in heating furnaces. The historical image collection module of the system obtains the normal combustion area of the furnace fire in the heating furnace from the historical combustion image, and respectively calculates the thresholds for evaluating whether the furnace tube has reached the rupture state according to the area and flame brightness; the real-time image acquisition module shoots the real-time combustion image in the heating furnace based on visible light imaging, determines the real-time combustion area of the furnace fire in the heating furnace, and respectively calculates the parameters representing the evaluation of the degree of rupture according to the current combustion area area and the current flame brightness; the evaluation result generation module obtains the evaluation result of the current furnace tube rupture state by comparing the real-time combustion area with the normal combustion area, as well as the parameters and thresholds. The present invention adopts visible light imaging to realize accurate monitoring of the rupture state of the furnace tube and ensure the safe production of the heating furnace.
[0035] Embodiment 1
[0036] Figure 1 Schematic diagram of the overall structure of the system for monitoring furnace tube rupture in the heating furnace according to the embodiment of the present application. Figure 1 The system for monitoring the rupture of furnace tubes in a heating furnace according to the present invention is described in detail.
[0037] In this embodiment, the system for monitoring the rupture of furnace tubes in a heating furnace includes at least: a historical image collection module 10, a real-time image acquisition module 20, and an evaluation result generation module 30. First, the historical image collection module 10 collects historical combustion images of the heating furnace to be monitored when the furnace tubes are not ruptured, thereby determining the normal combustion area in each historical image, and calculating the area and flame brightness of the normal combustion area. Based on this, a first threshold for evaluating whether the furnace tube has reached a rupture state according to the area and a second threshold for evaluating whether the furnace tube has reached a rupture state according to the flame brightness are obtained respectively. Afterwards, the real-time image acquisition module 20 acquires the real-time combustion images of the heating furnace to be monitored, thereby determining the real-time combustion area in each real-time image, and calculating the first parameter and the second parameter of the current combustion area area and the current flame brightness respectively. The first / second parameters are used to represent parameters for evaluating the degree of the rupture state according to the current combustion area area / current flame brightness. Finally, the evaluation result generation module 30 obtains the evaluation result of the current furnace tube rupture status by respectively comparing the real-time combustion area determined by the real-time image acquisition module 20 with the normal combustion area determined by the historical image collection module 10, the first parameter calculated by the real-time image acquisition module 20 with the first threshold calculated by the historical image collection module 10, and the second parameter calculated by the real-time image acquisition module 20 with the second threshold calculated by the historical image collection module 10.
[0038] In the actual production process, when the furnace tube in the heating furnace is broken, an abnormal combustion flame will be generated. When the abnormal combustion flame overlaps with the normal combustion area covered by the original normal combustion flame in the heating furnace, the area of the normal combustion area will increase and the brightness will increase; when the abnormal combustion flame does not overlap with the normal combustion area covered by the original normal combustion flame in the heating furnace, the combustion flame (i.e., the abnormal combustion flame) can be monitored outside the normal combustion area. Therefore, the present invention is based on visible light imaging to capture the combustion image in the heating furnace, so as to identify in real time whether the furnace tube rupture generates an abnormal combustion flame based on the captured combustion image, thereby overcoming the defects of inaccurate monitoring results caused by the fragility and drift of thermocouples in monitoring furnace tube ruptures through thermocouples, infrared photography or empirical data, the high cost defect of infrared photography or the defect that empirical data cannot be monitored in real time, and realizes furnace tube rupture monitoring based on visible light.
[0039] The historical image collection module 10 collects the historical combustion images of the heating furnace to be monitored when the furnace tube is not broken, so as to determine the normal combustion area in each historical image, and calculate the area and flame brightness of the normal combustion area, based on which, respectively obtain the first threshold value for evaluating whether the furnace tube has reached the broken state according to the area and the second threshold value for evaluating whether the furnace tube has reached the broken state according to the flame brightness. In the embodiment of the present application, the historical image collection module 10 first screens the combustion images in the heating furnace to be monitored when the furnace tube is not broken in the historical operation data of the heating furnace to be monitored pre-shot based on the visible light imaging method, and collects the screened combustion images as historical combustion images. After completing the collection of historical combustion images, the historical image collection module 10 determines the normal combustion area on the image for each historical combustion image (i.e.: the normal combustion area covered by the original normal combustion flame in the heating furnace), and calculates the area and flame brightness of the normal combustion area according to the currently determined normal combustion area. Combined with the aforementioned characteristics of the influence of abnormal combustion flames on the normal combustion area in the actual production process, it can be seen that the normal combustion area, the area and flame brightness of the normal combustion area can all be used as evaluation criteria for whether the furnace tube has reached the broken state. Therefore, the present invention uses the calculated area of the normal combustion area as the first threshold for evaluating whether the furnace tube has reached a rupture state based on the area, and uses the calculated flame brightness of the normal combustion area as the second threshold for evaluating whether the furnace tube has reached a rupture state based on the flame brightness.
[0040] Further, the historical image collection module 10 extracts the RGB values of the historical combustion images, and analyzes the brightness difference between each pixel and all the pixels adjacent to the pixel for each historical combustion image, so that when the brightness of the current pixel is higher than all the pixels corresponding to it, the Boolean variable at the location of the current pixel is activated, and finally the Boolean variable of each historical combustion image is obtained to determine the normal combustion area, the first threshold and the second threshold. Specifically, after completing the collection of historical combustion images, the historical image collection module 10 extracts the RGB value of each historical combustion image. After obtaining the RGB value of each historical combustion image, the historical image collection module 10 compares the brightness difference between each pixel constituting the current historical combustion image and all the pixels adjacent to the current pixel for each historical combustion image, and then activates the Boolean variable at the location of the current pixel when the brightness of the current pixel is higher than all the pixels corresponding to it. Afterwards, the historical image collection module 10 identifies all activated Boolean variables on each historical combustion image, obtains the normal combustion area, and then obtains the corresponding first threshold and second threshold.
[0041] Next, the historical image collection module 10 also uses the training data set in the historical combustion image to train the preset model to obtain a recognition model for identifying the normal combustion area, the first threshold and the second threshold, and then uses the recognition model to extract the normal combustion area, the first threshold and the second threshold in the test data set in the historical combustion image, and then according to the currently extracted prediction results, the normal combustion area, the first threshold and the second threshold determined based on the Boolean variables are corrected respectively.
[0042] After completing the collection of historical combustion images, the historical image collection module 10 divides all the collected historical combustion images into a training data set and a test data set, and then uses the training data set to train the preset model. In the process of training the preset model, the historical image collection module 10 is based on the preset model, uses the historical combustion images in the training data set as the input information of the preset model, and uses the normal combustion area, the first threshold and the second threshold as the output information of the preset model, thereby obtaining a recognition model through training the preset model. That is to say, this embodiment uses the historical combustion images in the training data set as the input information of the preset machine learning model (the current preset machine learning model is the preset model), substitutes it into the preset model, starts training the preset model, and obtains the recognition model after the training is completed.
[0043] After the recognition model is obtained by training the preset model, the historical image collection module 10 uses the historical combustion images in the test data set as the input information of the recognition model and substitutes them into the recognition model, thereby extracting the normal combustion area, the first threshold value and the second threshold value using the recognition model. Further, the normal combustion area, the first threshold value and the second threshold value identified by the recognition model are analyzed and compared with the normal combustion area, the first threshold value and the second threshold value analyzed using the Boolean variable, so that the normal combustion area, the first threshold value and the second threshold value identified by the recognition model are corrected to obtain the accurate normal combustion area, the first threshold value and the second threshold value.
[0044] Furthermore, the historical image collection module 10 also regularly collects the real-time combustion images that have completed the rupture state evaluation and uses them as historical combustion images to update the recognition model. In the application embodiment, the historical image collection module 10 presets the image collection time. The historical image collection module regularly collects the real-time combustion images that have completed the rupture state evaluation according to the preset image collection time and uses them as historical combustion images to update the recognition model, which effectively ensures the adaptability of the recognition result to the actual working condition and improves the accuracy of the recognition result.
[0045] In an embodiment of the present application, the historical image collection module 10 also collects real-time combustion images of the monitored heating furnace when each furnace tube is not broken, and uses each real-time combustion image with an unbroken state evaluation result as a historical combustion image to redefine the normal combustion area, and recalculate the area and flame brightness of the normal combustion area, so as to update the normal combustion area, the first threshold and the second threshold obtained by using the original historical combustion image in real time, thereby effectively improving the updating efficiency of the recognition model while ensuring the adaptability of the recognition result to the actual working conditions and improving the accuracy of the recognition result.
[0046] The real-time image acquisition module 20 acquires the real-time combustion image of the heating furnace to be monitored, thereby determining the real-time combustion area in each real-time image, and respectively calculating the first parameter and the second parameter of the current combustion area area and the current flame brightness, and the first / second parameter is used to represent the parameter for evaluating the degree of the rupture state according to the current combustion area area / current flame brightness. In an embodiment of the present application, the real-time image acquisition module 20 shoots the real-time combustion image in the heating furnace to be monitored based on the visible light imaging method. When each real-time combustion image is obtained, the real-time image acquisition module 20 determines the real-time combustion area on the image (i.e., the real-time combustion area covered by the real-time combustion flame in the heating furnace) for the current real-time combustion image, and calculates the area and flame brightness of the real-time combustion area according to the currently determined real-time combustion area, so that the calculated area of the real-time combustion area is used as the first parameter for representing the degree of the rupture state according to the current combustion area area, and the calculated flame brightness of the real-time combustion area is used as the second parameter for representing the degree of the rupture state according to the current flame brightness.
[0047] Furthermore, the real-time image acquisition module 20 includes: a first acquisition unit 21 , a second acquisition unit 22 and a parameter correction unit 23 . The first acquisition unit 21 is used to extract the RGB value of the real-time image, based on which, for each real-time image, the brightness difference between each pixel and all the pixels adjacent to the pixel is analyzed, so that when the brightness of the current pixel is higher than that of all the corresponding pixels, the Boolean variable at the location of the current pixel is activated to obtain the Boolean variable of each real-time image, so as to determine the first type of real-time combustion area, the first type of first parameter and the first type of second parameter related to the brightness difference; the second acquisition unit 22 is used to extract the RGB value of the real-time image, and for each real-time image, the brightness gradient of each pixel is analyzed, so that when the brightness gradient of the pixel is greater than zero, the Boolean variable at the location of the current pixel is activated to obtain the Boolean variable of each real-time image, so as to determine the second type of real-time combustion area, the second type of first parameter and the second type of second parameter related to the brightness gradient; the parameter correction unit 23 is used to analyze and compare the first type of real-time combustion area with the second type of real-time combustion area, the first type of first parameter with the second type of first parameter, and the first type of second parameter with the second type of second parameter, respectively, to obtain the best real-time combustion area, the best first parameter and the best second parameter for evaluating the actual rupture state of the current furnace tube, and output them.
[0048] First, when the real-time image acquisition module 20 collects the real-time combustion image, the first acquisition unit 21 extracts the RGB value of the real-time combustion image. After obtaining the RGB value of each real-time combustion image, the first acquisition unit 21 compares the brightness of each pixel constituting the current real-time combustion image and the brightness difference between all the pixels adjacent to the current pixel in a Boolean variable activation method similar to the historical image collection module 10, and then activates the Boolean variable at the location of the current pixel when the brightness of the current pixel is higher than all the corresponding pixels. After that, the first acquisition unit 21 identifies all activated Boolean variables on the current real-time combustion image, and obtains the first type of real-time combustion area, the first type of first parameter, and the first type of second parameter related to the brightness difference.
[0049] Secondly, when the real-time image acquisition module 20 acquires the real-time combustion image, the second acquisition unit 22 and the first acquisition unit 21 simultaneously extract the RGB value of the same real-time combustion image. After obtaining the RGB value of each real-time combustion image, the second acquisition unit 22 calculates the corresponding image brightness value according to the RGB value, and then uses the image brightness value to calculate the brightness gradient of each pixel constituting the current real-time combustion image, and then activates the Boolean variable at the location of the current pixel when the brightness gradient of the current pixel is greater than zero. After that, the second acquisition unit 22 identifies all activated Boolean variables on the current real-time combustion image to obtain the flame outline, and then obtains the second type of real-time combustion area, the second type of first parameter and the second type of second parameter related to the brightness gradient.
[0050] Finally, the parameter correction unit 23 analyzes and compares the position distribution relationship between the first type of real-time combustion area and the second type of real-time combustion area, the data size relationship between the first type of first parameter and the second type of first parameter, and the data size relationship between the first type of second parameter and the second type of second parameter based on the first type of real-time combustion area, the first type of first parameter and the first type of second parameter related to the brightness difference generated by the first acquisition unit 21, and the second type of real-time combustion area, the second type of first parameter and the second type of second parameter related to the brightness gradient generated by the second acquisition unit 22, to obtain the optimal real-time combustion area, the optimal first parameter and the optimal second parameter for evaluating the actual rupture state of the current furnace tube, so as to obtain accurate furnace tube rupture state evaluation results using the optimal real-time combustion area, the optimal first parameter and the optimal second parameter.
[0051] In a specific embodiment of the present application, when acquiring the RGB values of the corresponding combustion images, the historical image collection module 10 and the real-time image acquisition module 20 use the point function return value in VB to obtain the R, G, and B values of the corresponding combustion images.
[0052] In the embodiment of the present application, the average brightness of each pixel in the normal combustion area is used as the flame brightness of the corresponding normal combustion area, and the average brightness of each pixel in the real-time combustion area is used as the flame brightness of the corresponding real-time combustion area. The brightness of each pixel is calculated using the following expression:
[0053] L=0.299R+0.587G+0.144B (1)
[0054] Among them, L represents the brightness of the pixel, R represents the brightness of the red channel, G represents the brightness of the green channel, and B represents the brightness of the blue channel.
[0055] The evaluation result generation module 30 obtains the evaluation result of the current furnace tube rupture state by comparing the real-time combustion area with the normal combustion area, the first parameter with the first threshold, and the second parameter with the second threshold. In the embodiment of the present application, the evaluation result generation module 30 uses the method of comparing and analyzing the real-time combustion area with the normal combustion area as the first analysis method, the method of comparing and analyzing the first parameter with the first threshold as the second analysis method, and the method of comparing and analyzing the second parameter with the second threshold as the third analysis method, so as to compare the real-time furnace tube rupture state obtained by using the first analysis method, the second analysis method, and the third analysis method, and finally obtain an accurate evaluation result of the current furnace tube rupture state.
[0056] Further, the evaluation result generation module 30 includes an analysis unit 31. The analysis unit 31 determines whether there is an overlap between the normal combustion area and the real-time combustion area, wherein when there is no overlap, it is determined that the current furnace tube is in a ruptured state, and when there is an overlap, it is also diagnosed whether the current furnace tube is in a ruptured state by judging the magnitude relationship between the first parameter and the first threshold value, and the magnitude relationship between the second parameter and the second threshold value, wherein if the first parameter is greater than the first threshold value and the second parameter is less than the second threshold value, it is determined that the current furnace tube is in a ruptured state; if the first parameter is less than the first threshold value and the second parameter is greater than the second threshold value, it is determined that the current furnace tube is in a ruptured state; if the first parameter is greater than the first threshold value and the second parameter is greater than the second threshold value, it is determined that the current furnace tube is in a ruptured state. Specifically, the analysis unit 31 first determines whether there is an overlap between the normal combustion area and the real-time combustion area according to the first analysis method (i.e., determines the positional relationship between the normal combustion area and the real-time combustion area). When there is no overlap, that is, the real-time combustion area is outside the normal combustion area, it is determined that the current furnace tube is in a ruptured state. When there is an overlap, that is, the real-time combustion area is within the normal combustion area or there is a partial overlap between the two, the analysis unit 31 continues to determine the size relationship between the first parameter and the first threshold according to the second analysis method, and determines the size relationship between the second parameter and the second threshold according to the third analysis method to diagnose whether the current furnace tube is in a ruptured state. When the real-time combustion area is within the normal combustion area or there is a partial overlap between the two, and the size relationship between the second parameter and the second threshold satisfies the following conditions, it is determined that the current furnace tube is in a ruptured state: (1) the first parameter is greater than the first threshold and the second parameter is less than the second threshold; (2) the first parameter is less than the first threshold and the second parameter is greater than the second threshold; (3) the first parameter is greater than the first threshold and the second parameter is greater than the second threshold.
[0057] The system for monitoring the rupture of furnace tubes in a heating furnace according to the present invention further includes an alarm module. When the alarm module determines that the furnace tube is in a ruptured state, it alarms for the current ruptured state, and generates a first alarm message for alarming the ruptured state when there is no overlap phenomenon, or generates a second alarm message for alarming the ruptured state when there is an overlap phenomenon. In practical applications, whether there is an overlap phenomenon between the normal combustion area and the real-time combustion area can reflect the severity of the rupture of the furnace tube to a certain extent. Therefore, when the evaluation result generation module 30 determines that the furnace tube is in a ruptured state, the alarm module of this embodiment generates a first alarm message for alarming the ruptured state when there is no overlap phenomenon, or generates a second alarm message for alarming the ruptured state when there is an overlap phenomenon, based on the basis for forming the current evaluation result, thereby realizing the alarm prompt for the ruptured state and the alarm feedback for the severity of the rupture of the furnace tube reflected by the current ruptured state in the alarm process.
[0058] The system for monitoring furnace tube rupture in a heating furnace of the present invention is arranged in the heating furnace to be monitored, and the tolerable temperature thereof is greater than or equal to 1500°C.
[0059] Furthermore, the system for monitoring furnace tube rupture in a heating furnace according to the present invention satisfies the following conditions at the same time when it is arranged in the heating furnace to be monitored:
[0060]
[0061] L monitor ≥ 0.6 L vis (3)
[0062] Among them, L monitor represents the height of the real-time image acquisition module in the heating furnace, R represents the inner diameter of the heating furnace, R1 represents the radius of the furnace nozzle in the heating furnace, and L vis represents the fire height, θ represents the field of view of the real-time image acquisition module, and θ1 represents the depression angle of the real-time image acquisition module.
[0063] Embodiment 2
[0064] In a specific embodiment of the present application, according to the system for monitoring the rupture of furnace tubes in a heating furnace described in the aforementioned embodiment 1, the system for monitoring the rupture of furnace tubes in a heating furnace of this embodiment is arranged in the heating furnace to be monitored currently. In the embodiment of the present application, the inner diameter of the heating furnace to be monitored is 5m, the radius of the furnace nozzle is 4m, the height of the furnace fire is 1.5m, the field of view is 120°, and the depression angle is 20°. It is calculated that the installation height of the system for monitoring the rupture of furnace tubes in a heating furnace in the heating furnace to be monitored should be higher than 0.84m. According to the arrangement method described in this embodiment, the system for monitoring the rupture of furnace tubes in a heating furnace is arranged in the heating furnace to be monitored currently, and an evaluation result of the rupture state of the furnace tubes that conforms to the actual situation is obtained. Therefore, the present invention can provide technical support for the layout range setting of the monitoring system related to the implementation of on-site monitoring.
[0065] Embodiment 3
[0066] In a specific embodiment of the present application, according to the system for monitoring the rupture of furnace tubes in a heating furnace described in the first embodiment, the system for monitoring the rupture of furnace tubes in a heating furnace of the present embodiment is deployed in the heating furnace to be monitored to obtain the evaluation result of the rupture state of the furnace tubes of the heating furnace to be monitored. Specifically, the historical image collection module 10 calculates that the area of the normal combustion area is 3.2m 2 The real-time image acquisition module 20 calculates that the area of the real-time burning area is 3m 2 . Moreover, the real-time combustion area determined by the real-time image acquisition module 20 is outside the normal combustion area determined by the historical image collection module 10. It can be seen that the furnace tube of the currently monitored heating furnace is broken outside the normal combustion area. At this time, the evaluation result generation module 30 generates an evaluation result that the current furnace tube is in a broken state. In summary, the present invention realizes accurate monitoring of the broken state of the furnace tube and ensures the safe production of the heating furnace.
[0067] Embodiment 4
[0068] On the other hand, based on the system for monitoring furnace tube rupture in a heating furnace described in the aforementioned embodiment 1, an embodiment of the present invention further proposes a method for monitoring furnace tube rupture in a heating furnace. The method utilizes the above-mentioned system for monitoring furnace tube rupture in a heating furnace to effectively realize accurate monitoring of the furnace tube rupture status of the heating furnace. Figure 2 It is a step diagram of a method for monitoring furnace tube rupture in a heating furnace according to an embodiment of the present application.
[0069] like Figure 2As shown, the method for monitoring the rupture of furnace tubes in a heating furnace according to the present invention comprises the following steps: Step S210 uses a historical image collection module to collect historical combustion images of the heating furnace to be monitored when the furnace tubes are not ruptured, thereby determining the normal combustion area in each historical image, and calculating the area and flame brightness of the normal combustion area, based on which, respectively obtain a first threshold for evaluating whether the furnace tube has reached a rupture state according to the area and a second threshold for evaluating whether the furnace tube has reached a rupture state according to the flame brightness; Step S220 uses a real-time image acquisition module to acquire real-time combustion images of the heating furnace to be monitored, thereby determining the real-time combustion area in each real-time image, and respectively calculates a first parameter and a second parameter of the current combustion area area and the current flame brightness, the first / second parameters being used to represent parameters for evaluating the degree of rupture according to the current combustion area area / current flame brightness; Step S230 The evaluation result generation module obtains the evaluation result of the current furnace tube rupture state by respectively comparing the real-time combustion area of step S220 with the normal combustion area of step S210, the first parameter of step S220 with the first threshold of step S210, and the second parameter of step S220 with the second threshold of step S210.
[0070] In step S210, the historical image collection module is used to collect historical combustion images of the heating furnace to be monitored when the furnace tube is not broken, so as to determine the normal combustion area in each historical image, and calculate the area and flame brightness of the normal combustion area. In this embodiment, the historical image collection module is used to extract the RGB value of the historical combustion image, and for each historical combustion image, the brightness difference between each pixel point and all the pixels adjacent to the pixel point is analyzed, so that when the brightness of the current pixel point is higher than that of all the corresponding pixels, the Boolean variable at the position of the current pixel point is activated, and finally the Boolean variable of each historical combustion image is obtained to determine the normal combustion area, the first threshold value and the second threshold value.
[0071] Embodiment 5
[0072] The embodiment of the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by a processor to implement the operation of monitoring the furnace tube rupture in the heating furnace performed in the method of the above embodiment. For example, the computer-readable storage medium can be ROM (Read Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc-Read Only Memory), magnetic tape, floppy disk and optical data storage device, etc.
[0073] The present invention proposes a system, method and storage medium for monitoring the rupture of furnace tubes in a heating furnace. The historical image collection module of the system obtains the normal combustion area of the furnace fire in the heating furnace from the historical combustion image, and respectively calculates the threshold value for evaluating whether the furnace tube has reached the rupture state according to the area and the flame brightness; the real-time image acquisition module shoots the real-time combustion image in the heating furnace based on visible light imaging, determines the real-time combustion area of the furnace fire in the heating furnace, and respectively calculates the parameters representing the evaluation of the degree of rupture according to the current combustion area area and the current flame brightness; the evaluation result generation module obtains the evaluation result of the current furnace tube rupture state by comparing the real-time combustion area with the normal combustion area, and the parameters with the threshold value. The present invention adopts the visible light imaging method to realize the accurate monitoring of the furnace tube rupture state and ensure the safe production of the heating furnace. In addition, the monitoring method adopted by the present invention has high reliability and low cost, solves the problem of inaccurate monitoring results caused by the drift of high-temperature airflow and the influence of the furnace fire environment on the reflectivity, and is an important support for industrial safety, efficiency and clean production. At the same time, the selection of the monitoring equipment adopted by the present invention and the layout method in the heating furnace provide technical support for the layout range setting of the monitoring system related to the implementation of on-site monitoring.
[0074] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any person familiar with the technology within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0075] It should be understood that the embodiments disclosed in the present invention are not limited to the specific structures, processing steps or materials disclosed herein, but should be extended to equivalent substitutions of these features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.
[0076] The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.
[0077] Although the embodiments disclosed in the present invention are as above, the contents described are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the technical field to which the present invention belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present invention, but the patent protection scope of the present invention shall still be subject to the scope defined in the attached claims.
Claims
1. A system for monitoring furnace tube rupture in a heating furnace, characterized in that: include: A historical image collection module, which is used to collect historical combustion images of the heating furnace to be monitored when the furnace tube is not broken, so as to determine the normal combustion area in each historical image, and calculate the area and flame brightness of the normal combustion area, based on which, a first threshold value for evaluating whether the furnace tube has reached a broken state according to the area and a second threshold value for evaluating whether the furnace tube has reached a broken state according to the flame brightness are obtained respectively; A real-time image acquisition module, which is used to acquire the real-time combustion image of the heating furnace to be monitored, so as to determine the real-time combustion area in each real-time image, and respectively calculate the first parameter and the second parameter of the current combustion area area and the current flame brightness, wherein the first / second parameter is used to represent the parameter for evaluating the degree of the rupture state according to the current combustion area area / current flame brightness; An evaluation result generating module is used to obtain an evaluation result of the current furnace tube rupture state by respectively comparing the real-time combustion area with the normal combustion area, the first parameter with the first threshold, and the second parameter with the second threshold.
2. The system according to claim 1, characterized in that The arrangement position of the system in the heating furnace to be monitored satisfies the following conditions at the same time: L monitor ≥0.6L vis Among them, L monitor represents the height of the real-time image acquisition module in the heating furnace, R represents the inner diameter of the heating furnace, R1 represents the radius of the furnace nozzle in the heating furnace, and L vis represents the fire height, θ represents the field of view of the real-time image acquisition module, and θ1 represents the depression angle of the real-time image acquisition module.
3. The system according to claim 1 or 2, characterized in that: The historical image collection module is also used to extract the RGB values of the historical combustion images, and analyze the brightness difference between each pixel and all the pixels adjacent to the pixel for each historical combustion image, so that when the brightness of the current pixel is higher than that of all the corresponding pixels, the Boolean variable at the position of the current pixel is activated, and finally the Boolean variable of each historical combustion image is obtained to determine the normal combustion area, the first threshold and the second threshold.
4. The system according to claim 3, characterized in that The historical image collection module is also used to train a preset model using a training data set in the historical combustion image to obtain a recognition model for identifying the normal combustion area, the first threshold and the second threshold, thereby using the recognition model to extract the normal combustion area, the first threshold and the second threshold in the test data set in the historical combustion image, and then correct the normal combustion area, the first threshold and the second threshold determined based on the Boolean variable according to the currently extracted prediction results.
5. The system according to claim 4, characterized in that The historical image collection module is further used to periodically collect real-time combustion images that have completed rupture state evaluation and use them as the historical combustion images to update the recognition model.
6. The system according to any one of claims 1 to 5, characterized in that: The real-time image acquisition module comprises: A first acquisition unit is used to extract the RGB value of the real-time image, based on which, for each real-time image, analyzes the brightness difference between each pixel and all the pixels adjacent to the pixel, so that when the brightness of the current pixel is higher than that of all the corresponding pixels, the Boolean variable at the position of the current pixel is activated to obtain the Boolean variable of each real-time image, so as to determine the first type of real-time combustion area, the first type of first parameter and the first type of second parameter related to the brightness difference; a second acquisition unit, which is used to extract the RGB value of the real-time image, and analyze the brightness gradient of each pixel point for each real-time image, so as to activate the Boolean variable at the position of the current pixel point when the brightness gradient of the pixel point is greater than zero, to obtain the Boolean variable of each real-time image, so as to determine the second type of real-time combustion area, the second type of first parameter and the second type of second parameter related to the brightness gradient; A parameter correction unit is used to analyze and compare the first type of real-time combustion area with the second type of real-time combustion area, the first type of first parameter with the second type of first parameter, and the first type of second parameter with the second type of second parameter, respectively, to obtain the best real-time combustion area, the best first parameter and the best second parameter for evaluating the actual rupture state of the current furnace tube, and output them.
7. The system according to any one of claims 1 to 6, characterized in that: The evaluation result generation module comprises: An analysis unit is used to determine whether there is overlap between the normal combustion area and the real-time combustion area, wherein: When there is no overlap, it is determined that the current furnace tube is in a ruptured state. When there is an overlap phenomenon, whether the current furnace tube is in a ruptured state is diagnosed by judging the magnitude relationship between the first parameter and the first threshold value, and the magnitude relationship between the second parameter and the second threshold value, wherein: If the first parameter is greater than the first threshold value and the second parameter is less than the second threshold value, it is determined that the current furnace tube is in a ruptured state; If the first parameter is less than the first threshold value and the second parameter is greater than the second threshold value, it is determined that the current furnace tube is in a ruptured state; If the first parameter is greater than the first threshold value and the second parameter is greater than the second threshold value, it is determined that the current furnace tube is in a ruptured state.
8. The system according to claim 7, characterized in that The system further comprises: The alarm module is used to alarm for the current ruptured state when it is determined that the furnace tube is in a ruptured state, and generate a first alarm message for alarming the ruptured state when there is no overlap phenomenon, or generate a second alarm message for alarming the ruptured state when there is an overlap phenomenon.
9. The system according to any one of claims 1 to 8, characterized in that: The system has a temperature tolerance greater than or equal to 1500°C.
10. The system according to any one of claims 1 to 9, characterized in that: The flame brightness of the normal combustion area is the average brightness of each pixel point in the corresponding combustion area, and the flame brightness of the real-time combustion area is the average brightness of each pixel point in the corresponding combustion area.
11. A method for monitoring tube rupture in a heating furnace, characterized in that: The method is implemented using the system according to any one of claims 1 to 10, wherein the method comprises: The historical image collection module is used to collect historical combustion images of the heating furnace to be monitored when the furnace tube is not broken, so as to determine the normal combustion area in each historical image, and calculate the area and flame brightness of the normal combustion area, based on which, a first threshold value for evaluating whether the furnace tube has reached a broken state according to the area and a second threshold value for evaluating whether the furnace tube has reached a broken state according to the flame brightness are obtained respectively; A real-time combustion image of the heating furnace to be monitored is obtained by using a real-time image acquisition module, so as to determine the real-time combustion area in each real-time image, and respectively calculate a first parameter and a second parameter of the current combustion area area and the current flame brightness, wherein the first / second parameter is used to represent a parameter for evaluating the degree of the rupture state according to the current combustion area area / current flame brightness; The evaluation result generation module obtains the evaluation result of the current furnace tube rupture state by respectively comparing the real-time combustion area with the normal combustion area, the first parameter with the first threshold, and the second parameter with the second threshold.
12. The method according to claim 11, characterized in that The step of using the historical image collection module to collect historical combustion images of the heating furnace to be monitored when the furnace tube is not broken, thereby determining the normal combustion area in each historical image, and calculating the area and flame brightness of the normal combustion area includes: The historical image collection module is used to extract the RGB values of the historical combustion images, and for each historical combustion image, the brightness difference between each pixel and all the pixels adjacent to the pixel is analyzed. When the brightness of the current pixel is higher than that of all the corresponding pixels, the Boolean variable at the position of the current pixel is activated, and finally the Boolean variable of each historical combustion image is obtained to determine the normal combustion area, the first threshold and the second threshold.
13. A computer-readable storage medium, characterized in that: It contains a series of instructions for executing the method steps for monitoring tube rupture in a heating furnace as claimed in claim 11 or 12.