Combustor flame judgment method and system

Abstract

The invention provides a burner flame judgment method and system, and belongs to the technical field of heating furnaces. The method comprises the steps that a target heating furnace is monitored, a monitoring video is obtained, and the monitoring video comprises combustion images of all furnace nozzles of the target heating furnace; a plurality of image recognition algorithms are used for recognizing the combustion images of the furnace nozzles, and a plurality of flame morphology recognition results corresponding to the furnace nozzles are obtained; and based on the multiple flame morphology recognition results, whether the corresponding furnace nozzles are extinguished or not is judged, and a judgment result is obtained. The combustion images of all the furnace nozzles are recognized through a plurality of image recognition algorithms, and accurate judgment of extinguishing of flames of all the furnace nozzles is achieved through the image recognition algorithms. And judging whether the target heating furnace is abnormally extinguished or not according to the judgment result corresponding to each furnace nozzle. And due to the accuracy of each judgment result, the judgment results corresponding to all the furnace nozzles can be utilized to accurately judge that the flame of the target heating furnace is extinguished.

Description

Technical Field

[0001] The invention relates to the technical field of heating furnaces, and in particular to a burner flame judgment method and system. Background Art

[0002] The components of a heating furnace are generally divided into five parts, namely, the radiation chamber, the convection chamber, the burner, the waste heat recovery system and the ventilation system. The burner is an important component of the heating furnace, which can generate heat and is composed of three parts: the fuel nozzle, the air distributor and the combustion channel. Existing heating furnaces are usually equipped with multiple nozzles. For the overall heating furnace, when the flames of all the nozzles are extinguished, it is considered that the flame of the heating furnace is abnormally extinguished. However, due to various reasons such as coke accumulation, blockage, air, fuel and hot air in the furnace, the flame of the nozzle will present various forms, and the setting of the nozzle is usually compact, so it is impossible to accurately judge the state of each nozzle flame. If you wait until the flames of the nozzles are all extinguished to the naked eye before judging that the flame of the heating furnace is abnormally extinguished, not only will it waste energy due to failure to cut off the power or shut down the equipment in time, but it will also easily cause damage to the furnace shell and furnace tubes, resulting in increased maintenance costs for the heating furnace, and even shortening the service life of the heating furnace, and may even cause fire or explosion.

[0003] Therefore, how to accurately determine whether each nozzle of the heating furnace is extinguished to determine whether the heating furnace is abnormally extinguished is a problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a burner flame judgment method and system to at least solve the above-mentioned problem that the state of each furnace nozzle flame cannot be accurately judged, which leads to the inability to accurately judge whether the heating furnace is abnormally extinguished.

[0005] In order to achieve the above object, the present invention provides a burner flame judgment method in a first aspect, comprising:

[0006] Monitor the target heating furnace to obtain a monitoring video, which includes combustion images of all furnace nozzles of the target heating furnace;

[0007] Using multiple image recognition algorithms to recognize the combustion images of each furnace nozzle respectively, and obtaining multiple flame morphology recognition results corresponding to each furnace nozzle;

[0008] Based on multiple flame shape recognition results, determine whether the corresponding furnace nozzle is extinguished and obtain a determination result;

[0009] According to the determination results corresponding to each furnace nozzle, it is determined whether the target heating furnace is abnormally extinguished.

[0010] Optionally, the burner flame judgment method further includes:

[0011] Decompose the surveillance video into multiple consecutive image frames;

[0012] Grayscale processing is performed on multiple image frames to obtain grayscale processing results, and the combustion images corresponding to each furnace nozzle are determined according to the grayscale processing results.

[0013] Optionally, the above-mentioned monitoring of the target heating furnace to obtain the monitoring video includes:

[0014] At least one camera is used to monitor the target heating furnace to obtain a monitoring video.

[0015] Optionally, the above-mentioned using at least one camera to monitor the target heating furnace to obtain a monitoring video includes:

[0016] The target heating furnace is monitored by a first camera to obtain a first video;

[0017] According to the shooting angle and installation position of the first camera, a second camera group is configured, wherein the second camera group includes at least one second camera;

[0018] Using all second cameras in the second camera group to monitor the target heating furnace to obtain a second video;

[0019] The first video and the second video are combined to obtain a surveillance video.

[0020] Optionally, the above-mentioned using at least one camera to monitor the target heating furnace to obtain a monitoring video includes:

[0021] A plurality of cameras are used to monitor the target heating furnace to obtain monitoring videos collected by each camera, wherein each camera is configured with a corresponding image recognition algorithm.

[0022] Optionally, the above-mentioned determining whether the corresponding furnace nozzle is extinguished based on the multiple flame morphology recognition results to obtain the determination result includes:

[0023] If the multiple flame shape recognition results are all that the furnace nozzle is extinguished, then the judgment result is that the furnace nozzle is extinguished;

[0024] If the multiple flame shape recognition results are all that the furnace nozzle is not extinguished, then the judgment result is that the furnace nozzle is not extinguished;

[0025] If the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are judged to identify abnormal flame shape recognition results and non-abnormal flame shape recognition results;

[0026] Whether the furnace nozzle is extinguished is determined based on the abnormal flame morphology recognition results and the non-abnormal flame morphology recognition results.

[0027] Optionally, if the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are judged to identify abnormal flame shape recognition results and non-abnormal flame shape recognition results, including:

[0028] If the multiple flame shape recognition results are inconsistent, a preliminary judgment is performed on the multiple flame shape recognition results to obtain a preliminary judgment result;

[0029] When the preliminary judgment result is that the multiple flame shape recognition results do not belong to the suspected abnormal image, the multiple flame shape recognition results are input into the preset database for matching to determine whether the furnace nozzle is extinguished;

[0030] If the preliminary judgment result is that multiple flame shape recognition results belong to suspected abnormal images, a secondary judgment is performed on each flame shape recognition result to obtain a secondary judgment result;

[0031] According to the secondary judgment result, the abnormal flame morphology recognition result and the non-abnormal flame morphology recognition result are judged.

[0032] Optionally, if the multiple flame shape recognition results are inconsistent, a preliminary judgment is performed on the multiple flame shape recognition results to obtain a preliminary judgment result, including:

[0033] Generate line graph data using multiple flame shape recognition results according to a preset arrangement order;

[0034] Compare the line chart data with the preset standard line chart to obtain the comparison result;

[0035] Based on the comparison results, a preliminary judgment is made as to whether the multiple flame morphology recognition results belong to suspected abnormal images, and a preliminary judgment result is obtained.

[0036] Optionally, after determining the abnormal flame morphology recognition result and the non-abnormal flame morphology recognition result based on the secondary judgment result, the method further includes:

[0037] Abnormal flame morphology recognition results are discarded, and non-abnormal flame morphology recognition results are added to the preset standard line chart.

[0038] Optionally, if the preliminary judgment result is that multiple flame shape recognition results belong to suspected abnormal images, a secondary judgment is performed on each flame shape recognition result to obtain a secondary judgment result, including:

[0039] After adjusting the process parameters of the furnace nozzle, a combustion test image of the furnace nozzle is obtained;

[0040] Use various image recognition algorithms to recognize the combustion test images respectively, and obtain the corresponding flame morphology test recognition results;

[0041] For any image recognition algorithm, the corresponding flame morphology test recognition results are compared with the corresponding multiple standard images to obtain multiple comparison results;

[0042] Based on multiple comparison results, it is judged whether the flame profile test recognition result is abnormal, so as to determine whether the flame profile recognition result corresponding to the image recognition algorithm is abnormal, and obtain a secondary judgment result.

[0043] Optionally, the above-mentioned multiple image recognition algorithms include at least one or more of Otsu's method, Boolean variable method and Yolo V5 algorithm.

[0044] Optionally, judging whether the target heating furnace is abnormally extinguished according to the judgment results corresponding to each furnace nozzle includes:

[0045] When all determination results are that the furnace nozzle is extinguished, it is determined that the target heating furnace is abnormally extinguished, and an abnormal alarm signal is issued. Otherwise, it is determined that the target heating furnace is not abnormally extinguished.

[0046] A second aspect of the present invention provides a burner flame judgment system, comprising:

[0047] A monitoring video acquisition module is used to monitor the target heating furnace and obtain a monitoring video, wherein the monitoring video includes combustion images of all furnace nozzles of the target heating furnace;

[0048] An image recognition module is used to recognize the combustion images of each furnace nozzle using multiple image recognition algorithms to obtain multiple flame morphology recognition results corresponding to each furnace nozzle;

[0049] A furnace nozzle extinguishing determination module is used to determine whether the corresponding furnace nozzle is extinguished based on multiple flame morphology recognition results to obtain a determination result;

[0050] The heating furnace abnormal extinguishing judgment module is used to judge whether the target heating furnace is abnormally extinguished according to the judgment results corresponding to each furnace nozzle.

[0051] In a third aspect of the present invention, a machine-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the burner flame judgment method.

[0052] In a fourth aspect of the present invention, an electronic device is provided. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the burner flame judgment method is implemented.

[0053] Through the above technical scheme, a burner flame judgment method and system include: monitoring a target heating furnace to obtain a monitoring video, wherein the monitoring video includes the combustion images of all the nozzles of the target heating furnace. Using multiple image recognition algorithms to recognize the combustion images of each nozzle, multiple flame morphology recognition results corresponding to each nozzle are obtained. For each nozzle, the flame morphology recognition results obtained by recognizing the corresponding combustion images by each image recognition algorithm are combined to comprehensively determine whether the nozzle is extinguished, that is, the judgment result of the nozzle. Thus, the combustion images of each nozzle are recognized by multiple image recognition algorithms, and the extinguishing of the flame of each nozzle is accurately determined by using multiple image recognition algorithms. According to the judgment results corresponding to each nozzle, it is determined whether the target heating furnace is abnormally extinguished. Since the judgment results of each nozzle are obtained by combining the comprehensive judgment of multiple image recognition algorithms, the accuracy of the judgment results of each nozzle is guaranteed. Then, using the judgment results corresponding to all nozzles, it is possible to accurately determine whether the target heating furnace is abnormally extinguished, thereby achieving the purpose of accurately determining the extinguishing of the flame of the target heating furnace.

[0054] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0056] Figure 1 It is a flow chart of a burner flame judgment method provided by one embodiment of the present invention;

[0057] Figure 2 It is a block diagram of a burner flame judgment system provided by one embodiment of the present invention;

[0058] Figure 3 It is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.

[0059] Description of Reference Numerals

[0060] 10 - electronic device, 100 - processor, 101 - memory, 102 - computer program. DETAILED DESCRIPTION

[0061] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0062] Example 1

[0063] Figure 1 FIG. 1 is a flow chart of a burner flame judgment method provided by an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a burner flame judgment method, comprising:

[0064] S110: monitoring the target heating furnace to obtain a monitoring video, where the monitoring video includes combustion images of all furnace nozzles of the target heating furnace;

[0065] The burner flame judgment method further includes: decomposing the monitoring video into a plurality of continuous image frames, performing grayscale processing on the plurality of image frames to obtain grayscale processing results, and determining the combustion image corresponding to each burner nozzle according to the grayscale processing results.

[0066] Specifically, the monitoring video is first decompressed and decomposed into multiple continuous image frames. Then, grayscale processing is performed on any image frame to obtain a grayscale processing result, and the grayscale value of each pixel on the image frame is identified. According to the grayscale value of each pixel, the overlapping parts and non-overlapping parts of adjacent furnace nozzles in the image frame are determined. According to the overlapping parts and non-overlapping parts of any furnace nozzle, the combustion area of ​​the furnace nozzle during actual combustion is determined. Therefore, the combustion image of the furnace nozzle can be obtained by combining the combustion area corresponding to any furnace nozzle in all image frames.

[0067] S120: using multiple image recognition algorithms to respectively recognize the combustion images of each furnace nozzle, and obtaining multiple flame morphology recognition results corresponding to each furnace nozzle;

[0068] Among them, the above-mentioned multiple image recognition algorithms include at least one or more of Otsu's method, Boolean variable method and Yolo V5 algorithm.

[0069] S130: Based on the multiple flame shape recognition results, determine whether the corresponding furnace nozzle is extinguished, and obtain a determination result;

[0070] Specifically, for each furnace nozzle, the flame morphology recognition results obtained by combining the corresponding combustion images recognized by various image recognition algorithms can be used to comprehensively determine whether the furnace nozzle is extinguished, that is, the determination result of the furnace nozzle. Thus, the combustion images of each furnace nozzle are recognized separately by multiple image recognition algorithms, and the multiple image recognition algorithms are used to achieve accurate determination of the extinguishment of the flame of each furnace nozzle.

[0071] S140: Determine whether the target heating furnace is abnormally extinguished according to the determination results corresponding to each furnace nozzle.

[0072] Among them, the above-mentioned judgment result corresponding to each furnace nozzle is used to judge whether the target heating furnace is abnormally extinguished, including: when each judgment result is that the furnace nozzle is extinguished, it is judged that the target heating furnace is abnormally extinguished and an abnormal alarm signal is issued at the same time; otherwise, it is judged that the target heating furnace is not abnormally extinguished.

[0073] Specifically, the flame of the target heating furnace is judged in combination with the judgment results corresponding to each furnace nozzle. If the flames of all furnace nozzles are extinguished, it is judged that the flame of the target heating furnace is abnormally extinguished, and an abnormal alarm signal is issued to remind the user to handle it. On the contrary, if the flames of all furnace nozzles are not completely extinguished, it is judged that the flame of the target heating furnace is not abnormally extinguished. Since the judgment results of each furnace nozzle are obtained by comprehensive judgment in combination with multiple image recognition algorithms, the accuracy of the judgment results of each furnace nozzle is guaranteed. Then, using the judgment results corresponding to all furnace nozzles, it is possible to accurately determine whether the target heating furnace is abnormally extinguished, thereby achieving the purpose of accurately judging the extinguishment of the flame of the target heating furnace.

[0074] Example 2

[0075] This embodiment provides a burner flame judgment method, which is basically the same as the burner flame judgment method provided in Embodiment 1, and the main difference is that: the above-mentioned monitoring of the target heating furnace to obtain the monitoring video includes:

[0076] At least one camera is used to monitor the target heating furnace to obtain a monitoring video.

[0077] As an implementation mode of this embodiment, the above-mentioned use of at least one camera to monitor the target heating furnace to obtain a monitoring video includes:

[0078] The target heating furnace is monitored by a first camera to obtain a first video;

[0079] According to the shooting angle and installation position of the first camera, a second camera group is configured, wherein the second camera group includes at least one second camera;

[0080] Using all second cameras in the second camera group to monitor the target heating furnace to obtain a second video;

[0081] The first video and the second video are combined to obtain a surveillance video.

[0082] Specifically, the first camera is configured to monitor the target heating furnace. According to the shooting angle and installation position of the first camera, the shooting blind area of ​​the first camera can be determined. Therefore, the second camera group is configured for the shooting blind area of ​​the first camera. Therefore, the monitoring video is obtained by combining the first video shot by the first camera and the second video shot by the second camera group. It is ensured that the monitoring video completely captures the overall combustion process of the target heating furnace.

[0083] As another implementation of this embodiment, the above-mentioned use of at least one camera to monitor the target heating furnace to obtain a monitoring video includes:

[0084] A plurality of cameras are used to monitor the target heating furnace to obtain monitoring videos collected by each camera, wherein each camera is configured with a corresponding image recognition algorithm.

[0085] Specifically, a target heating furnace is monitored using a plurality of different cameras, and different camera configurations use different image recognition algorithms. The image recognition algorithm configured for each camera is used to recognize the monitoring video collected by the corresponding camera.

[0086] Example 3

[0087] This embodiment provides a burner flame judgment method, which is basically the same as the burner flame judgment method provided in Embodiment 1, and the main difference is that: the above method is based on multiple flame morphology recognition results to judge whether the corresponding burner nozzle is extinguished, and the judgment result is obtained, including:

[0088] If the multiple flame shape recognition results are all that the furnace nozzle is extinguished, then the judgment result is that the furnace nozzle is extinguished;

[0089] If the multiple flame shape recognition results are all that the furnace nozzle is not extinguished, then the judgment result is that the furnace nozzle is not extinguished;

[0090] Specifically, for any furnace nozzle, the NooN method is used to determine that the flame is extinguished, that is, if all flame morphology recognition results corresponding to the furnace nozzle are that the furnace nozzle is extinguished, then the furnace nozzle is determined to be extinguished.

[0091] If the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are judged to identify abnormal flame shape recognition results and non-abnormal flame shape recognition results;

[0092] In some implementations of the present embodiment, if the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are judged to identify the abnormal flame shape recognition result and the non-abnormal flame shape recognition result, including: if the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are preliminarily judged to obtain a preliminary judgment result. When the preliminary judgment result is that the multiple flame shape recognition results do not belong to the suspected abnormal image, the multiple flame shape recognition results are input into the preset database for matching to determine whether the furnace nozzle is extinguished. Among them, the preset database stores the furnace nozzle judgment results corresponding to different flame shape recognition results of multiple image recognition algorithms. If the preliminary judgment result is that the multiple flame shape recognition results belong to the suspected abnormal image, the flame shape recognition results are secondary judged to obtain the secondary judgment result. According to the secondary judgment result, the abnormal flame shape recognition result and the non-abnormal flame shape recognition result are judged.

[0093] Wherein, if the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are preliminarily judged to obtain a preliminary judgment result, including: generating line graph data using the multiple flame shape recognition results in a preset arrangement order. Comparing the line graph data with a preset standard line graph to obtain a comparison result. Based on the comparison result, preliminarily judging whether the multiple flame shape recognition results belong to suspected abnormal images to obtain a preliminary judgment result.

[0094] Specifically, for any furnace nozzle, when multiple flame shape recognition results are inconsistent, multiple flame shape recognition results are arranged in a preset order (for example, the results obtained by the Otsu method are arranged first, then the results obtained by the Boolean variable method are arranged, and then the results obtained by the yolo V5 algorithm are arranged) to obtain line graph data, and then the line graph data is compared with the preset standard line graph to obtain a comparison result, which can characterize the trend difference between the trend of the line graph data and the preset standard line graph. If the trend difference between the trend of the line graph data and the preset standard line graph is greater than the preset deviation, all these flame shape recognition results are determined to be suspected abnormal images. On the contrary, if the trend difference between the trend of the line graph data and the preset standard line graph is within the range of the preset deviation, it is determined that these flame shape recognition results do not belong to suspected abnormal images. Thereby, the screening of suspected abnormal images is achieved.

[0095] In this embodiment, the above-mentioned preset standard line graph is drawn by using the recognition results of each image recognition algorithm for the normal combustion of the furnace nozzle. The preset standard line graph may include multiple line data, which indicate the recognition results of each image recognition algorithm under different and normal combustion conditions of the furnace nozzle.

[0096] In addition, if the preliminary judgment result is that multiple flame shape recognition results belong to suspected abnormal images, a secondary judgment is performed on each flame shape recognition result to obtain a secondary judgment result, including:

[0097] After adjusting the process parameters of the furnace nozzle, a combustion test image of the furnace nozzle is obtained;

[0098] Use various image recognition algorithms to recognize the combustion test images respectively, and obtain the corresponding flame morphology test recognition results;

[0099] For any image recognition algorithm, the corresponding flame morphology test recognition results are compared with the corresponding multiple standard images to obtain multiple comparison results;

[0100] Among them, the standard image corresponding to any image recognition algorithm is an image of the furnace nozzle flame burning normally recognized by the image recognition algorithm under various pre-acquired situations (for example: changing the gas size, gas density, gas concentration, etc. input to the furnace nozzle).

[0101] Based on multiple comparison results, it is judged whether the flame profile test recognition result is abnormal, so as to determine whether the flame profile recognition result corresponding to the image recognition algorithm is abnormal, and obtain a secondary judgment result.

[0102] Specifically, the furnace nozzle corresponding to the flame shape recognition result of the secondary judgment is recalibrated to wait for the image to be collected again. The front end adjusts the process parameters of the calibrated furnace nozzle (for example: the input gas size, gas density, gas concentration, etc.), and then ignites the furnace nozzle again to obtain the combustion test image of the furnace nozzle. The combustion test image is recognized by each image recognition algorithm to obtain the corresponding flame shape test recognition result. For any image recognition algorithm, the corresponding flame shape test recognition result is compared with the multiple standard images corresponding to the image recognition algorithm to obtain multiple comparison results. If the comparison results exceed the preset threshold, it indicates that the flame shape recognition result recognized by the image recognition algorithm is indeed an abnormal flame shape recognition result, so that through the secondary judgment, it is further judged whether each suspected abnormal image is really an abnormal flame shape recognition result. Then the purpose of identifying the abnormal flame shape recognition result and the non-abnormal flame shape recognition result from the multiple flame shape recognition results is achieved. Then the occurrence of misjudgment of flame extinction is prevented.

[0103] Whether the furnace nozzle is extinguished is determined based on the abnormal flame morphology recognition results and the non-abnormal flame morphology recognition results.

[0104] Specifically, the abnormal flame shape recognition results are discarded, and the non-abnormal flame shape recognition results are retained. All non-abnormal flame shape recognition results are input into a preset database (the preset database stores the furnace nozzle determination results corresponding to different flame shape recognition results of various image recognition algorithms) for matching to determine whether the furnace nozzle is extinguished.

[0105] In the above implementation process, if the user uses multiple cameras equipped with corresponding image recognition algorithms to monitor the target heating furnace and obtains the monitoring videos collected by each camera, if the result obtained by any image recognition algorithm is an abnormal flame morphology recognition result, it may be a problem with the camera (for example, the camera is damaged).

[0106] In some implementations of this embodiment, after determining the abnormal flame morphology recognition result and the non-abnormal flame morphology recognition result based on the secondary judgment result, the method further includes:

[0107] Abnormal flame morphology recognition results are discarded, and non-abnormal flame morphology recognition results are added to the preset standard line chart.

[0108] Specifically, the method discards abnormal flame shape recognition results, and marks non-abnormal flame shape recognition results as normal images and adds them to a preset standard line graph to further improve the accuracy of the determination.

[0109] Example 4

[0110] Figure 2 FIG. 1 is a block diagram of a burner flame judgment system provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides a burner flame judgment system, comprising:

[0111] A monitoring video acquisition module is used to monitor the target heating furnace and obtain a monitoring video, wherein the monitoring video includes combustion images of all furnace nozzles of the target heating furnace;

[0112] An image recognition module is used to recognize the combustion images of each furnace nozzle using multiple image recognition algorithms to obtain multiple flame morphology recognition results corresponding to each furnace nozzle;

[0113] A furnace nozzle extinguishing determination module is used to determine whether the corresponding furnace nozzle is extinguished based on multiple flame morphology recognition results to obtain a determination result;

[0114] The heating furnace abnormal extinguishing judgment module is used to judge whether the target heating furnace is abnormally extinguished according to the judgment results corresponding to each furnace nozzle.

[0115] Specifically, the flame of the target heating furnace is judged in combination with the judgment results corresponding to each furnace nozzle. If the flames of all furnace nozzles are extinguished, it is judged that the flame of the target heating furnace is abnormally extinguished, and an abnormal alarm signal is issued to remind the user to handle it. On the contrary, if the flames of all furnace nozzles are not completely extinguished, it is judged that the flame of the target heating furnace is not abnormally extinguished. Since the judgment results of each furnace nozzle are obtained by comprehensive judgment in combination with multiple image recognition algorithms, the accuracy of the judgment results of each furnace nozzle is guaranteed. Then, using the judgment results corresponding to all furnace nozzles, it is possible to accurately determine whether the target heating furnace is abnormally extinguished, thereby achieving the purpose of accurately judging the extinguishment of the flame of the target heating furnace.

[0116] Example 5

[0117] The embodiment of the present invention further provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the burner flame judgment method described above.

[0118] Machine-readable storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0119] An embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the burner flame judgment method described above is implemented.

[0120] like Figure 3 FIG. 1 is a schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiment are implemented.

[0121] Exemplarily, the computer program 102 may be divided into one or more modules / units, one or more modules / units are stored in the memory 101, and are executed by the processor 100 to complete the present invention. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the terminal device 10. For example, the computer program 102 may be divided into a monitoring video acquisition module, an image recognition module, a furnace nozzle extinguishing determination module, and a heating furnace abnormal extinguishing determination module.

[0122] The electronic device 10 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will appreciate that Figure 3It is only an example of the electronic device 10 and does not constitute a limitation of the electronic device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0123] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0124] The memory 101 may be an internal storage unit of the electronic device 10, such as a hard disk or memory of the electronic device 10. The memory 101 may also be an external storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 10. Further, the memory 101 may also include both an internal storage unit of the electronic device 10 and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the electronic device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0125] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0126] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0131] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A burner flame judgment method, characterized in that: include: Monitoring a target heating furnace to obtain a monitoring video, wherein the monitoring video includes combustion images of all furnace nozzles of the target heating furnace; Using multiple image recognition algorithms to recognize the combustion images of each furnace nozzle respectively, and obtaining multiple flame morphology recognition results corresponding to each furnace nozzle; Based on the multiple flame shape recognition results, determine whether the corresponding furnace nozzle is extinguished to obtain a determination result; According to the determination results corresponding to each furnace nozzle, it is determined whether the target heating furnace is abnormally extinguished.

2. The burner flame judgment method according to claim 1, characterized in that: Also includes: Decomposing the surveillance video into a plurality of continuous image frames; Grayscale processing is performed on the multiple image frames to obtain grayscale processing results, and the combustion image corresponding to each furnace nozzle is determined according to the grayscale processing results.

3. The burner flame judgment method according to claim 1, characterized in that: The monitoring of the target heating furnace to obtain the monitoring video includes: At least one camera is used to monitor the target heating furnace to obtain a monitoring video.

4. The burner flame judgment method according to claim 3, characterized in that: The method of monitoring the target heating furnace by using at least one camera to obtain a monitoring video includes: The target heating furnace is monitored by a first camera to obtain a first video; According to the shooting angle of view and the installation position of the first camera, a second camera group is configured, wherein the second camera group includes at least one second camera; Using all second cameras in the second camera group to monitor the target heating furnace to obtain a second video; The first video and the second video are combined to obtain a surveillance video.

5. The burner flame judgment method according to claim 3, characterized in that: The method of monitoring the target heating furnace by using at least one camera to obtain a monitoring video includes: A plurality of cameras are used to monitor the target heating furnace to obtain monitoring videos collected by each camera, wherein each camera is configured with a corresponding image recognition algorithm.

6. The burner flame judgment method according to claim 1, characterized in that: The step of determining whether the corresponding furnace nozzle is extinguished based on the plurality of flame shape recognition results to obtain a determination result includes: If the multiple flame shape recognition results are all that the furnace nozzle is extinguished, then the judgment result is that the furnace nozzle is extinguished; If the multiple flame shape recognition results are all that the furnace nozzle is not extinguished, then the determination result is that the furnace nozzle is not extinguished; If the multiple flame shape recognition results are inconsistent, judging the multiple flame shape recognition results to identify abnormal flame shape recognition results and non-abnormal flame shape recognition results; Whether the furnace nozzle is extinguished is determined according to the abnormal flame morphology recognition result and the non-abnormal flame morphology recognition result.

7. The burner flame judgment method according to claim 6, characterized in that: If the multiple flame shape recognition results are inconsistent, the multiple flame shape recognition results are judged to identify abnormal flame shape recognition results and non-abnormal flame shape recognition results, including: If the multiple flame shape recognition results are inconsistent, performing a preliminary judgment on the multiple flame shape recognition results to obtain a preliminary judgment result; When the preliminary judgment result is that the multiple flame shape recognition results do not belong to the suspected abnormal image, the multiple flame shape recognition results are input into the preset database for matching to determine whether the furnace nozzle is extinguished; If the preliminary judgment result is that the multiple flame shape recognition results belong to suspected abnormal images, a secondary judgment is performed on each flame shape recognition result to obtain a secondary judgment result; According to the secondary judgment result, the abnormal flame morphology recognition result and the non-abnormal flame morphology recognition result are judged.

8. The burner flame judgment method according to claim 7, characterized in that: If the multiple flame shape recognition results are inconsistent, a preliminary judgment is performed on the multiple flame shape recognition results to obtain a preliminary judgment result, including: Generate line graph data using the plurality of flame shape recognition results in a preset arrangement order; Comparing the line graph data with a preset standard line graph to obtain a comparison result; Based on the comparison result, it is preliminarily determined whether the multiple flame shape recognition results belong to suspected abnormal images, and a preliminary determination result is obtained.

9. The burner flame judgment method according to claim 8, characterized in that: After determining the abnormal flame shape recognition result and the non-abnormal flame shape recognition result according to the secondary judgment result, the method further includes: The abnormal flame morphology recognition result is discarded, and the non-abnormal flame morphology recognition result is added to a preset standard line graph.

10. The burner flame judgment method according to claim 7, characterized in that: If the preliminary judgment result is that the multiple flame shape recognition results belong to suspected abnormal images, a secondary judgment is performed on each flame shape recognition result to obtain a secondary judgment result, including: After adjusting the process parameters of the furnace nozzle, a combustion test image of the furnace nozzle is obtained; Using various image recognition algorithms to respectively recognize the combustion test images, and obtain corresponding flame morphology test recognition results; For any image recognition algorithm, the corresponding flame morphology test recognition results are compared with the corresponding multiple standard images to obtain multiple comparison results; Based on the multiple comparison results, it is judged whether the flame shape test recognition result is abnormal, so as to determine whether the flame shape recognition result corresponding to the image recognition algorithm is abnormal, and obtain a secondary judgment result.

11. The burner flame judgment method according to claim 1, characterized in that: The multiple image recognition algorithms include at least one or more of Otsu's method, Boolean variable method and Yolo V5 algorithm.

12. The burner flame judgment method according to claim 1, characterized in that: The step of judging whether the target heating furnace is abnormally extinguished according to the judgment results corresponding to each furnace nozzle includes: When all determination results are that the furnace nozzle is extinguished, it is determined that the target heating furnace is abnormally extinguished, and an abnormal alarm signal is issued. Otherwise, it is determined that the target heating furnace is not abnormally extinguished.

13. A burner flame judgment system, characterized in that: include: A monitoring video acquisition module, used to monitor the target heating furnace and obtain a monitoring video, wherein the monitoring video includes combustion images of all furnace nozzles of the target heating furnace; An image recognition module is used to recognize the combustion images of each furnace nozzle using multiple image recognition algorithms to obtain multiple flame morphology recognition results corresponding to each furnace nozzle; A furnace nozzle extinguishing determination module, used to determine whether the corresponding furnace nozzle is extinguished based on the multiple flame morphology recognition results, and obtain a determination result; The heating furnace abnormal extinguishing judgment module is used to judge whether the target heating furnace is abnormally extinguished according to the judgment results corresponding to each furnace nozzle.

14. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the burner flame judgment method according to any one of claims 1 to 12.

15. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the burner flame judgment method according to any one of claims 1 to 12 is implemented.

Images