Hearth flame detection and combustion control method, device, equipment and medium

Abstract

The invention discloses a hearth flame detection and combustion control method and device, equipment and a medium, and the method comprises the steps: obtaining a flame image at a fire observation hole of a target hearth, and separating a flame region in the flame image from a hearth wall surface; extracting an ultraviolet branch, a visible light branch and a near-infrared branch in the flame area; outputting a flame stability index based on the ultraviolet branch, the visible light branch and the near-infrared branch; determining a flame propagation speed; constructing an optimal control function according to the flame stability index and the flame propagation speed; and under a preset constraint condition, solving the optimization control function to obtain an optimal control target. The invention belongs to the field of hearth flame control. According to the method, the flame stability can be evaluated, and the combustion strategy can be adjusted.

Description

Technical Field

[0001] The present invention relates to the field of furnace flame control, and in particular to a furnace flame detection and combustion control method, device, equipment and medium. Background Art

[0002] The furnace, also known as the combustion chamber, is the primary space in a boiler or industrial furnace where fuel is burned. It's an enclosed area constructed of refractory materials, designed to withstand high temperatures and ensure efficient and complete combustion of the fuel. Inside the furnace, the fuel mixes with air and ignites, releasing heat. This heat is typically used to convert water into steam (in a boiler), which in turn drives a turbine to generate electricity or is used for other processes requiring thermal energy.

[0003] Currently, furnace flame detection relies primarily on single infrared or ultraviolet sensors, which are susceptible to furnace dust, burner coking, and flame flicker noise, leading to false positives and missed detection of real flames. Therefore, to improve safety, the present invention provides a furnace flame detection and combustion control method. Summary of the Invention

[0004] The present invention solves the technical problem of the single means of detecting the flame in the furnace in the prior art by providing a furnace flame detection and combustion control method, device, equipment and medium, and achieves the technical effect of reducing the risk of furnace explosion.

[0005] In a first aspect, the present invention provides a furnace flame detection and combustion control method, comprising: Acquire a flame image at the target furnace fire viewing hole, and separate the flame area from the furnace wall in the flame image; Extracting the ultraviolet branch, visible light branch and near-infrared branch in the flame region; Based on the ultraviolet branch, visible light branch and near infrared branch, the flame stability index is output; Determine flame propagation velocity; Construct an optimization control function based on the flame stability index and flame propagation speed; Under the preset constraints, the optimization control function is solved to obtain the optimal control target.

[0006] Furthermore, the flame area in the flame image is separated from the furnace wall, including: Acquire the background image of the target furnace fire viewing hole when it is not burning; Subtract the flame image from the background image at pixel level to obtain a difference image; Convert the difference image into a binary image; Remove isolated noise points in binary images based on opening operations, and fill holes in binary images based on closing operations; Extract continuous pixel regions from binary images; The continuous pixel area is screened based on the color feature and texture feature to obtain the flame area in the flame image.

[0007] Furthermore, the ultraviolet branch, visible light branch, and near infrared branch in the flame region are extracted, including: Acquiring a flame image based on a multispectral camera, wherein the flame image includes images of several bands; Denoise, white balance correction and radiation positioning of band images; Get the flame area mask of the flame area; The flame area mask is mapped to the band image to obtain the ultraviolet branch, visible light branch and near-infrared branch.

[0008] Furthermore, based on the ultraviolet branch, the visible light branch, and the near-infrared branch, a flame stability index is output, including:

[0009] in, is the flame stability index, is the image standard deviation of the UV branch, is the image standard deviation of the visible light branch, is the average gray value of the visible light branch, is the area change rate of the near-infrared branch.

[0010] Furthermore, the flame propagation speed is determined, including:

[0011] in, is the flame propagation speed, is the empirical coefficient, is the oxygen concentration, is the flame temperature, For calorific value.

[0012] Furthermore, the flame stability index and flame propagation speed are used to construct an optimization control function, including:

[0013] in, To optimize the control function, to are weights, is the flame stability index, is the concentration of wind powder, is the nitrogen oxide emission concentration.

[0014] Furthermore, preset constraints include: Oxygen content range: 3.5% ≤ ≤5.5%; Coal ratio deviation is less than or equal to 8%; The flame center offset is less than or equal to 5% of the furnace width.

[0015] In a second aspect, the present invention provides a furnace flame detection and combustion control device, comprising: An acquisition module is used to acquire a flame image at a target furnace fire viewing hole and separate the flame area from the furnace wall in the flame image; An extraction module, used to extract the ultraviolet branch, visible light branch and near infrared branch in the flame area; An output module, for outputting a flame stability index based on an ultraviolet branch, a visible light branch, and a near infrared branch; Velocity propagation module, used to determine the flame propagation velocity; Function construction module, used to construct optimization control function based on flame stability index and flame propagation speed; The optimization module is used to solve the optimization control function under preset constraints to obtain the optimal control target.

[0016] In a third aspect, the present invention provides an electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor is configured to execute to implement a furnace flame detection and combustion control method as provided in the first aspect.

[0017] In a fourth aspect, the present invention provides a non-temporary computer-readable storage medium. When the instructions in the non-temporary computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a furnace flame detection and combustion control method as provided in the first aspect.

[0018] One or more technical solutions provided in the present invention have at least the following technical effects or advantages: The optimization control function provided by the present invention comprehensively considers four key factors: combustion stability, air-powder concentration, pollutant emissions, and flame propagation speed, and is used to guide the optimal control of the combustion process. Among them, the higher the FSI (flame stability index), the more stable the combustion. (100-FSI) is used in the objective function to normalize the index to facilitate optimization calculation; the air-powder concentration C affects combustion efficiency and safety. Too high may lead to incomplete combustion, while too low may cause the risk of flameout; NOx reflects the level of nitrogen oxide emissions and is an important indicator for measuring environmental performance; the flame propagation speed reflects the combustion response characteristics and affects the boiler's load regulation capability. The present invention is suitable for the design of intelligent control strategies for combustion systems such as coal-fired boilers, and helps to achieve efficient, clean, and stable combustion operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flow chart of a furnace flame detection and combustion control method provided by the present invention; Figure 2 This is a structural schematic diagram of a furnace flame detection and combustion control device provided by the present invention. DETAILED DESCRIPTION

[0021] The embodiment of the present invention solves the technical problem of the single detection means for the flame in the furnace in the prior art by providing a furnace flame detection and combustion control method.

[0022] The technical solution of the present invention is to solve the above technical problems, and the overall idea is as follows: A furnace flame detection and combustion control method comprises: acquiring a flame image at a target furnace fire viewing hole, and separating the flame region in the flame image from the furnace wall; extracting ultraviolet branches, visible light branches, and near-infrared branches in the flame region; outputting a flame stability index based on the ultraviolet branches, visible light branches, and near-infrared branches; determining a flame propagation speed; constructing an optimization control function based on the flame stability index and the flame propagation speed; and solving the optimization control function under preset constraints to obtain an optimal control target.

[0023] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0024] First, the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0025] The present invention provides Figure 1 A furnace flame detection and combustion control method shown includes steps S11-S16: Step S11 , acquiring a flame image at a target furnace fire viewing hole, and separating the flame area from the furnace wall in the flame image.

[0026] A furnace viewing port is an opening or window installed in the furnace wall of a boiler or combustion equipment. It allows operators or automated monitoring systems to observe the flame status inside the furnace. Through the port, the color, shape, and distribution of the flame can be directly visually inspected. Existing combustion control systems can utilize sensors or cameras installed at the port to capture flame images.

[0027] The flame area in the flame image is separated from the furnace wall, including: obtaining a background image of the target furnace fire viewing hole when it is not burning; performing pixel-level subtraction between the flame image and the background image to obtain a differential image; converting the differential image into a binary image; removing isolated noise points in the binary image based on an opening operation, and filling holes in the binary image based on a closing operation; extracting continuous pixel areas in the binary image; and screening the continuous pixel areas based on color features and texture features to obtain the flame area in the flame image.

[0028] The purpose of acquiring the background image of the target furnace fire viewing hole when it is not burning is to establish a "clean" background model, that is, the image of the furnace wall when there is no flame.

[0029] The purpose of performing pixel-wise subtraction between the flame image and the background image to obtain a difference image is to highlight the changes in the flame relative to the background. Specifically, if the value of a pixel position is significantly different between the two images, it is considered that the position has changed (possibly due to the presence of the flame).

[0030] The difference results are converted into a binary form that is easy to handle for further analysis. A threshold can be set to convert the difference image into a binary image, where 1 represents the flame and 0 represents the furnace wall.

[0031] The purpose of removing isolated noise points in the binary image based on the opening operation and filling the holes in the binary image based on the closing operation is to remove noise and fill the holes in the flame area to make the flame outline clearer and more accurate.

[0032] Opening: Erosion followed by dilation. This is used to remove small noise points to prevent them from being mistaken for flames.

[0033] Closing: Dilation followed by erosion. This is used to fill small holes within the flame, making the flame area more continuous and complete.

[0034] The purpose of extracting continuous pixel areas in a binary image is to identify all possible flame areas. All continuous pixel blocks in a binary image can be extracted through connected domain analysis.

[0035] The purpose of screening continuous pixel areas based on color features and texture features to obtain the flame area in the flame image is to further screen out the real flame area and eliminate non-flame interference.

[0036] Color features: Flames usually have a specific color distribution (such as yellow, orange, etc.). The color information in the color space (such as HSV) can be used to distinguish flames from other objects.

[0037] Texture features: Flames are dynamic and irregular, and the discrimination can be enhanced by calculating local texture features (such as gray-level co-occurrence matrix GLCM).

[0038] Step S12: extracting the ultraviolet branch, visible light branch, and near infrared branch in the flame area.

[0039] Specifically, it includes: acquiring a flame image based on a multispectral camera, where the flame image includes several band images; denoising, white balance correction and radiation positioning of the band image; obtaining a flame area mask of the flame area; mapping the flame area mask to the band image to obtain an ultraviolet branch, a visible light branch and a near-infrared branch.

[0040] Use a multispectral camera to capture images of the flame in different wavelengths (UV, visible, near infrared) simultaneously or sequentially. A multispectral camera is able to capture images in one or more specific wavelength bands.

[0041] Denoising: In order to improve image quality, random noise in the image is removed. Methods can be Gaussian blur, median filtering, etc.

[0042] White balance correction: For the visible light band, ensure accurate color reproduction and avoid color deviation caused by changes in the color temperature of the light source. This can be achieved by adjusting the RGB values ​​of the image.

[0043] Radiometric calibration: Converting pixel values ​​into actual physical quantities (such as radiation intensity) can be calibrated using data from a preset standard source.

[0044] The purpose of obtaining the flame area mask of the flame area is to determine the specific location of the flame for subsequent accurate segmentation on images of different bands.

[0045] The background subtraction method or other image segmentation algorithms (such as threshold segmentation, edge detection, and machine learning models) can be used to generate a binary flame area mask.

[0046] The mask is a binary image of the same size as the original image, where 1 represents the flame area and 0 represents the non-flame area.

[0047] The flame area mask is mapped to the band image to obtain the ultraviolet branch, visible light branch and near-infrared branch. The purpose is to retain only the part corresponding to the flame area in each band image and remove background interference.

[0048] Step S13: outputting a flame stability index based on the ultraviolet branch, the visible light branch, and the near infrared branch.

[0049] Specifically include:

[0050] in, is the flame stability index, is the image standard deviation of the UV branch, is the image standard deviation of the visible light branch, is the average gray value of the visible light branch, is the area change rate of the near-infrared branch.

[0051] The ultraviolet branch reflects the intensity of the combustion chemical reaction; the visible light branch reflects the combustion deflection angle, symmetry and coking state of the burner area; the near-infrared branch reflects the flame temperature field and the movement trajectory of the coal powder particles.

[0052] in, It reflects the emission intensity of free radicals and is sensitive to early combustion reactions. The smaller the standard deviation, the more stable the ultraviolet radiation.

[0053] in, Reflects the distribution of high-temperature gas (near-infrared branch). The smaller the change in flame area, the more stable the combustion. in, Reflects the overall brightness and color of the flame (visible light branch). The higher the ratio, the higher the flame brightness and the smaller the fluctuation, and the more stable the combustion.

[0054] Step S14, determining the flame propagation speed.

[0055] Determine flame propagation velocity, including:

[0056] in, is the flame propagation speed, is the empirical coefficient, is the oxygen concentration, is the flame temperature, For calorific value.

[0057] In step S15 , an optimization control function is constructed based on the flame stability index and the flame propagation speed.

[0058] Based on the flame stability index and flame propagation speed, an optimization control function is constructed, including:

[0059] in, To optimize the control function, to are weights, is the flame stability index, is the concentration of wind powder, is the nitrogen oxide emission concentration.

[0060] The optimization control function provided by the present invention comprehensively considers four key factors: combustion stability, air-powder concentration, pollutant emissions, and flame propagation speed, and is used to guide the optimal control of the combustion process. Among them, the higher the FSI (flame stability index), the more stable the combustion. (100-FSI) is used in the objective function to normalize the index to facilitate optimization calculation; the air-powder concentration C affects combustion efficiency and safety. Too high may lead to incomplete combustion, while too low may cause the risk of flameout; NOx reflects the level of nitrogen oxide emissions and is an important indicator for measuring environmental performance; the flame propagation speed reflects the combustion response characteristics and affects the boiler's load regulation capability. The present invention is suitable for the design of intelligent control strategies for combustion systems such as coal-fired boilers, and helps to achieve efficient, clean, and stable combustion operation.

[0061] Step S16: Solve the optimization control function under preset constraints to obtain the optimal control target.

[0062] Preset constraints include: Oxygen content range: 3.5% ≤ ≤5.5%; coal ratio deviation is less than or equal to 8%; flame center offset is less than or equal to 5% of the furnace width.

[0063] Based on the preset constraints, the optimization control function is solved and the optimal control quantity can be solved by using model predictive control (MPC).

[0064] In summary, the present invention provides a furnace flame detection and combustion control method, including: acquiring a flame image at a target furnace fire viewing hole, and separating the flame area in the flame image from the furnace wall; extracting ultraviolet branches, visible light branches, and near-infrared branches in the flame area; outputting a flame stability index based on the ultraviolet branch, visible light branch, and near-infrared branch; determining the flame propagation speed; constructing an optimization control function based on the flame stability index and the flame propagation speed; solving the optimization control function under preset constraints to obtain the optimal control target. The optimization control function provided by the present invention comprehensively considers four key factors: combustion stability, air-powder concentration, pollutant emissions, and flame propagation speed, and is used to guide the optimal control of the combustion process. Among them, the higher the FSI (flame stability index), the more stable the combustion. (100-FSI) is used in the objective function to normalize the index to facilitate optimization calculation; the air-powder concentration C affects combustion efficiency and safety. Too high may lead to incomplete combustion, while too low may cause the risk of flameout; NOx reflects the level of nitrogen oxide emissions and is an important indicator for measuring environmental performance; the flame propagation speed reflects the combustion response characteristics and affects the boiler's load regulation capability. The present invention is suitable for the design of intelligent control strategies for combustion systems such as coal-fired boilers, and helps to achieve efficient, clean, and stable combustion operation.

[0065] Based on the same inventive concept, the present invention provides Figure 2 A furnace flame detection and combustion control device shown includes: An acquisition module 21 is used to acquire a flame image at a target furnace fire viewing hole and separate the flame area from the furnace wall in the flame image; An extraction module 22 is used to extract the ultraviolet branch, the visible light branch, and the near-infrared branch in the flame area; An output module 23 is configured to output a flame stability index based on the ultraviolet branch, the visible light branch, and the near infrared branch; a velocity propagation module 24 for determining the flame propagation velocity; A function construction module 25 is used to construct an optimization control function based on the flame stability index and the flame propagation speed; The optimization module 26 is used to solve the optimization control function under preset constraints to obtain the optimal control target.

[0066] Based on the same inventive concept, the present invention further provides an electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor is configured to execute to implement a furnace flame detection and combustion control method as provided above.

[0067] Based on the same inventive concept, the present invention also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by the processor of an electronic device, the electronic device can execute a furnace flame detection and combustion control method as provided above.

[0068] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiment of the present invention, based on the information processing method described in the embodiment of the present invention, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present invention will not be described in detail here. As long as the electronic device used by those skilled in the art to implement the information processing method in the embodiment of the present invention falls within the scope of protection of the present invention.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0071] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0074] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A furnace flame detection and combustion control method, characterized in that: include: Acquire a flame image at a target furnace fire viewing hole, and separate the flame area from the furnace wall in the flame image; extracting an ultraviolet branch, a visible light branch, and a near-infrared branch in the flame region; outputting a flame stability index based on the ultraviolet branch, the visible light branch, and the near infrared branch; Determine flame propagation velocity; constructing an optimization control function based on the flame stability index and the flame propagation speed; Under preset constraints, the optimization control function is solved to obtain the optimal control target.

2. A furnace flame detection and combustion control method according to claim 1, characterized in that: Separating the flame area from the furnace wall in the flame image includes: Acquire the background image of the target furnace fire viewing hole when it is not burning; Subtracting the flame image from the background image at pixel level to obtain a difference image; Convert the difference image into a binary image; Remove isolated noise points in binary images based on opening operations, and fill holes in binary images based on closing operations; Extract continuous pixel regions from binary images; Continuous pixel regions are screened based on color features and texture features to obtain flame regions in the flame image.

3. A furnace flame detection and combustion control method according to claim 1, characterized in that: Extracting the ultraviolet branch, the visible light branch, and the near infrared branch in the flame region includes: Acquiring a flame image based on a multispectral camera, wherein the flame image includes images of several bands; Denoise, white balance correction and radiation positioning of band images; Get the flame area mask of the flame area; The flame area mask is mapped to the band image to obtain the ultraviolet branch, visible light branch and near-infrared branch.

4. A furnace flame detection and combustion control method according to claim 1, characterized in that: Based on the ultraviolet branch, the visible light branch, and the near infrared branch, a flame stability index is output, including: in, is the flame stability index, is the image standard deviation of the UV branch, is the image standard deviation of the visible light branch, is the average gray value of the visible light branch, is the area change rate of the near-infrared branch.

5. A furnace flame detection and combustion control method according to claim 1, characterized in that: Determine flame propagation velocity, including: in, is the flame propagation speed, is the empirical coefficient, is the oxygen concentration, is the flame temperature, For calorific value.

6. A furnace flame detection and combustion control method according to claim 5, characterized in that: An optimization control function is constructed based on the flame stability index and the flame propagation speed, including: in, To optimize the control function, to are weights, is the flame stability index, is the concentration of wind powder, is the nitrogen oxide emission concentration.

7. A furnace flame detection and combustion control method according to claim 1, characterized in that: Preset constraints, including: Oxygen content range: 3.5% ≤ ≤5.5%; Coal ratio deviation is less than or equal to 8%; The flame center offset is less than or equal to 5% of the furnace width.

8. A furnace flame detection and combustion control device, characterized in that: include: An acquisition module is used to acquire a flame image at a target furnace fire viewing hole and separate the flame area from the furnace wall in the flame image; An extraction module, configured to extract an ultraviolet branch, a visible light branch, and a near-infrared branch in the flame region; an output module, configured to output a flame stability index based on the ultraviolet branch, the visible light branch, and the near-infrared branch; Velocity propagation module, used to determine the flame propagation velocity; A function construction module, configured to construct an optimization control function based on the flame stability index and the flame propagation speed; The optimization module is used to solve the optimization control function under preset constraints to obtain the optimal control target.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute and implement a furnace flame detection and combustion control method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that When the instructions in the non-transitory computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a furnace flame detection and combustion control method as claimed in any one of claims 1 to 7.

Images