Combustion control method, device and equipment for garbage power generation boiler and storage medium

Abstract

The invention discloses a garbage power generation boiler combustion control method, device and equipment and a storage medium, and relates to the technical field of garbage incineration power generation, and the garbage power generation boiler combustion control method comprises the steps that real-time image collection is conducted on a hearth of a garbage power generation boiler through a preset camera device with temperature calibration completed in advance, and a hearth monitoring image located at the tail section of garbage incineration combustion is obtained; based on the Planck black body radiation law and a preset temperature threshold value, temperature field calculation and flame segmentation are carried out on the hearth monitoring image; on the basis of a preset dust falling detection rule and the obtained segmented image, dust falling detection of the camera device is carried out, and when an obtained detection result shows that dust does not fall, live wire drawing is carried out on the segmented image by using a preset region of interest; and garbage combustion state analysis is conducted on the basis of the obtained drawn image, and an obtained analysis result including the live wire position is sent to a preset distributed control system so that the preset distributed control system can conduct fan frequency regulation and control. And the accuracy of combustion control is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of waste incineration power generation, and in particular to a combustion control method, device, equipment and storage medium for a waste power generation boiler. Background Art

[0002] At present, the domestic waste incineration power generation industry has entered a stage of rapid development, but with the rapid development of the industry, many problems have also been brought about, such as combustion control, etc. The immaturity or instability of technology may affect the operating efficiency and environmental protection effect of the project.

[0003] In the production stage, the temperature in the furnace is difficult to measure, and the air volume control during the waste incineration combustion stage is inaccurate. The temperature, wind pressure, oxygen content, steam volume and other data collected in the traditional furnace are difficult to reflect the actual situation of the furnace. The control strategy formulated by the distributed control system (DCS) based on the existing data is difficult to achieve good results for the fan air supply, feeding and pushing. The operator still needs to observe the real-time combustion video at the end of the combustion, determine the garbage combustion state and make manual adjustments, but in this way, it is difficult to achieve a high automation rate. It not only depends on the operator's supervisory experience, but also cannot guarantee the accuracy of control. In addition, ACC (Automatic Combustion Control, automatic control combustion system) can also be used to analyze video data, but it analyzes the flame height and flame color, not the precise temperature value. In addition, the use of neural networks requires a large amount of data and training time, has high hardware cost requirements, and fails to intuitively solve the existing problems that require a lot of investment from operators. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and storage medium for controlling combustion of a waste-to-energy boiler, which can realize automatic control of the fan frequency of the combustion section while solving the problem that the existing operation requires a large amount of input from operators, and improve the accuracy of combustion control. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a method for controlling combustion of a waste-to-energy boiler, comprising:

[0006] The furnace of the waste-to-energy boiler is captured in real time by a preset camera device that has been temperature-calibrated in advance, and a corresponding monitoring image of the furnace located at the end of the waste incineration combustion is obtained;

[0007] Based on Planck's blackbody radiation law and a preset temperature threshold, temperature field calculation and flame segmentation are performed on the furnace monitoring image to obtain a corresponding segmented image;

[0008] Perform dust detection on the camera device based on a preset dust detection rule and the segmented image, and when the obtained detection result indicates that the preset camera device is not dusted, perform line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image;

[0009] The garbage combustion state is analyzed based on the drawn image, and the obtained analysis results including the fire line position are sent to a preset distributed control system so that the preset distributed control system can adjust the fan frequency based on the analysis results to complete the corresponding combustion control operation.

[0010] Optionally, the furnace of the waste-to-energy boiler is captured in real time by a preset camera device that has completed temperature calibration in advance, so as to obtain a corresponding monitoring image of the furnace located at the end of the waste incineration combustion, including:

[0011] The furnace of the waste-to-energy boiler is imaged in real time by using a preset camera device that has been temperature calibrated in advance using Planck's blackbody radiation law, thereby obtaining a corresponding monitoring image of the furnace at the final stage of waste incineration.

[0012] Optionally, the temperature field calculation and flame segmentation are performed on the furnace monitoring image based on Planck's blackbody radiation law and a preset temperature threshold to obtain a corresponding segmented image, including:

[0013] Determine an initial temperature field corresponding to the furnace monitoring image based on Planck's blackbody radiation law; wherein the initial temperature field includes the temperature value of each pixel in the furnace monitoring image;

[0014] Each of the temperature values ​​is compared with a preset temperature threshold, and segmentation is performed using the comparison results corresponding to each of the pixels, so as to obtain a binary image as a segmented image.

[0015] Optionally, before performing dust detection on the camera device based on the preset dust detection rule and the segmented image, the method further includes:

[0016] Performing a union operation on the segmented image and the initial temperature field, and filling the black part with null values ​​to obtain a corresponding filled image;

[0017] Normalizing the temperature information in the filled image based on a preset main fire line normalization range and a preset secondary fire line normalization range to obtain a corresponding normalized image;

[0018] After coloring the segmented areas corresponding to the main fire line and the secondary fire line in the normalized image, the colored parts of the main fire line and the secondary fire line are merged to obtain a corresponding merged image.

[0019] Optionally, the performing dust detection on the camera device based on a preset dust detection rule and the segmented image includes:

[0020] Determining a corresponding dust falling detection area from the merged image based on a preset area demarcation rule, and cropping the merged image based on the dust falling detection area to obtain a corresponding cropped image;

[0021] Performing corresponding image normalization and smoothing filtering on the cropped image in sequence to obtain a corresponding filtered image;

[0022] Determine the gradient information of each pixel point in the filtered image in the horizontal and vertical directions by using the Sobel operator to obtain the gradient information corresponding to each pixel point in the filtered image and the corresponding average gradient information;

[0023] The gradient information and the average gradient information are judged based on the preset gradient threshold and the preset average gradient threshold respectively, so as to complete the corresponding dust falling detection using the obtained judgment results.

[0024] Optionally, when the obtained detection result indicates that the preset camera device is not covered with dust, performing line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image includes:

[0025] When the judgment result indicates that the number currently greater than the preset gradient threshold is greater than the preset number threshold, and the average gradient information is greater than the preset average gradient threshold, a detection result indicating that the preset camera device is not dusty is obtained;

[0026] After determining a preset region of interest in the filtered image based on preset configuration information and setting a corresponding range for the preset region of interest, primary and secondary fire line drawing is performed to obtain a corresponding drawn image.

[0027] Optionally, performing garbage combustion state analysis based on the drawn image and sending the obtained analysis result including the fire line position to a preset distributed control system includes:

[0028] Determine the corresponding firing line position based on the range information of the preset region of interest in the drawn image, the position information of the lowest point of the firing line, and the height of the drawn image;

[0029] In the process of performing corresponding flame area ratio analysis, average temperature analysis, maximum temperature analysis, and minimum temperature analysis using the preset region of interest in the drawn image, it is determined whether there is currently a burnout phenomenon by calculating the area between the main and auxiliary fire lines, so as to complete the corresponding garbage combustion state analysis operation and obtain the corresponding analysis results;

[0030] The analysis result is sent to a preset distributed control system based on a preset communication protocol.

[0031] In a second aspect, the present application provides a garbage power generation boiler combustion control device, comprising:

[0032] An image acquisition module is used to acquire real-time images of the furnace of the waste-to-energy boiler through a preset camera device that has completed temperature calibration in advance, and obtain a corresponding monitoring image of the furnace located at the end of the waste incineration combustion;

[0033] A segmented image acquisition module is used to perform temperature field calculation and flame segmentation on the furnace monitoring image based on Planck's blackbody radiation law and a preset temperature threshold to obtain a corresponding segmented image;

[0034] A dust falling detection module is used to perform dust falling detection on the camera device based on a preset dust falling detection rule and the segmented image, and when the obtained detection result indicates that the preset camera device is not dusted, perform line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image;

[0035] The combustion control module is used to analyze the garbage combustion status based on the drawn image, and send the obtained analysis results including the fire line position to a preset distributed control system, so that the preset distributed control system can adjust the fan frequency based on the analysis results to complete the corresponding combustion control operation.

[0036] In a third aspect, the present application provides an electronic device, including:

[0037] Memory, used to store computer programs;

[0038] The processor is used to execute the computer program to implement the steps of the aforementioned waste-to-energy boiler combustion control method.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the steps of the aforementioned waste-to-energy boiler combustion control method.

[0040] It can be seen that in this application, the furnace of the waste-to-energy boiler is collected in real time by a preset camera device that has completed temperature calibration in advance, and the corresponding furnace monitoring image located at the end of the waste incineration combustion is obtained; based on the Planck blackbody radiation law and the preset temperature threshold, the temperature field calculation and flame segmentation of the furnace monitoring image are respectively performed to obtain the corresponding segmented image; based on the preset ash detection rule and the segmented image, the camera device is detected for ash, and when the obtained detection result shows that the preset camera device has not fallen ash, the segmented image is drawn using the preset region of interest to obtain the corresponding drawn image; based on the drawn image, the garbage combustion state is analyzed, and the obtained analysis result including the position of the fire line is sent to the preset distributed control system, so that the preset distributed control system performs fan frequency regulation based on the analysis result to complete the corresponding combustion control operation. That is, in this application, the temperature field of the collected image is determined based on the preset camera device that has completed temperature calibration in advance and combined with the Planck blackbody radiation law, so as to determine the corresponding temperature information. Then, based on the preset ash detection rule, it is detected whether the preset camera device has fallen ash. Then, when the ash has not fallen, the garbage combustion state is analyzed by drawing the fire line, and the analysis results are sent to the preset distributed control system so that the preset distributed control system can use the analysis results to control the combustion of the furnace of the garbage power generation boiler. In this way, the fan frequency of the combustion section can be automatically controlled while solving the existing problem of requiring a lot of input from operators, and the accuracy of combustion control can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0042] Figure 1 A flow chart of a combustion control method for a waste-to-energy boiler provided in this application;

[0043] Figure 2 A schematic flow chart of a specific waste-to-energy boiler combustion control method provided in this application;

[0044] Figure 3 A schematic diagram of temperature field segmentation and calculation provided in this application;

[0045] Figure 4 A schematic diagram of a primary and secondary fire line coloring merging provided in this application;

[0046] Figure 5A schematic diagram of dust detection steps provided in this application;

[0047] Figure 6 A schematic diagram of a specific dust detection process provided for this application;

[0048] Figure 7 A schematic diagram of a drawn image provided by this application;

[0049] Figure 8 A schematic diagram of the corresponding relationship between the live wire position and the fan frequency control provided in this application;

[0050] Fig. 9 A schematic diagram of the structure of a combustion control device for a waste-to-energy boiler provided in this application;

[0051] Fig.10 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] The temperature, wind pressure, oxygen content, steam volume and other data collected by the traditional furnace are difficult to reflect the actual situation of the furnace. The control strategy formulated by the distributed control system based on the existing data is difficult to achieve good results for the fan air supply, feeding and pushing. The operator is still required to observe the real-time combustion video of the last stage of combustion, determine the garbage combustion state and make manual adjustments, but in this way, it is difficult to achieve a high automation rate. It not only depends on the operator's supervisory experience, but also cannot guarantee the accuracy of control. In addition, ACC can also be used to analyze video data, but it analyzes the flame height and flame color, not the precise temperature value. In addition, the use of neural networks requires a large amount of data and training time, has high hardware cost requirements, and fails to intuitively solve the existing problems that require a lot of investment from operators. To this end, the present application provides a garbage power generation boiler combustion control scheme, which can realize the automatic regulation of the fan frequency of the combustion section under the condition of solving the existing problems that require a lot of investment from operators, and improve the accuracy of combustion control.

[0054] See also Figure 1 As shown, the embodiment of the present invention discloses a combustion control method for a garbage power generation boiler, comprising:

[0055] Step S11, real-time image acquisition of the furnace of the waste-to-energy boiler is performed by a preset camera device that has completed temperature calibration in advance, so as to obtain a corresponding monitoring image of the furnace located at the end stage of waste incineration combustion.

[0056] Combination Figure 2 As shown, in this embodiment, the preset camera device is first used to collect images in real time, that is, the preset camera device that has completed temperature calibration in advance collects real-time images of the furnace of the waste-to-energy boiler to obtain the corresponding furnace monitoring image at the end of the waste incineration combustion, including: the preset camera device that has completed temperature calibration in advance using Planck's blackbody radiation law collects real-time images of the furnace of the waste-to-energy boiler to obtain the corresponding furnace monitoring image at the end of the waste incineration combustion. Among them, the preset camera device is pre-calibrated with temperature. Regarding temperature calibration, the temperature calculation formula shown below is derived according to Planck's blackbody radiation law:

[0057] ;

[0058] Among them, R and G are the red and green components of the RGB (Red Green Blue) image; λ r =700nm,λ g =546.1nm, respectively representing the wavelengths of red light and green light; C2 is the second radiation constant; K is a correction value, which is related to the camera parameters, exposure time, and spectral emissivity of the object being measured. When the fuel, the camera in the preset camera device, and the lens are determined, K, R / G and T correspond one to one, and the value of K changing with temperature can be calibrated experimentally.

[0059] The camera can be calibrated by temperature according to the above theory, or it can be calibrated manually. After the temperature calibration is completed, the temperature value corresponding to each pixel can be calculated based on the live video obtained by the camera.

[0060] Step S12: Based on Planck's blackbody radiation law and a preset temperature threshold, temperature field calculation and flame segmentation are performed on the furnace monitoring image to obtain a corresponding segmented image.

[0061] Specifically, after acquiring the video image, the temperature field of the furnace monitoring image needs to be calculated and segmented according to a given threshold, that is, the temperature field calculation and flame segmentation of the furnace monitoring image are performed based on Planck's blackbody radiation law and the preset temperature threshold to obtain the corresponding segmented image, including: determining the initial temperature field corresponding to the furnace monitoring image based on Planck's blackbody radiation law; wherein the initial temperature field includes the temperature value of each pixel in the furnace monitoring image; respectively comparing each temperature value with the preset temperature threshold, and using the comparison results corresponding to each pixel to perform segmentation to obtain a binary image after segmentation to obtain a flame field. wherein, combined with Figure 3 The schematic diagram shown shows the segmentation effect under different thresholds. It can be seen that the higher the preset temperature threshold, the smaller the segmentation portion is retained. Conversely, the lower the temperature, the smoother the segmentation. The threshold segmentation calculation formula is as follows:

[0062] ;

[0063] Among them, TH is the binary image obtained after segmentation; threshold is the preset temperature threshold, that is, the segmentation temperature; x (i, j) is the temperature value of the corresponding pixel point in the image, i is the horizontal coordinate, and j is the vertical coordinate.

[0064] Step S13, performing dust detection on the camera device based on preset dust detection rules and the segmented image, and when the obtained detection result indicates that the preset camera device is not dusty, performing line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image.

[0065] Combination Figure 2 As shown, it can be known that in this embodiment, after calculating the temperature field, ash detection needs to be performed. However, before performing ash detection, coloring is required first. That is, before performing ash detection on the camera device based on the preset ash detection rules and the segmented image, it also includes: performing a AND operation on the segmented image and the initial temperature field, and filling the black part with null values ​​to obtain a corresponding filled image; normalizing the temperature information in the filled image based on the preset main fire line normalization range and the preset secondary fire line normalization range to obtain a corresponding normalized image; after coloring the segmented areas corresponding to the main fire line and the secondary fire line in the normalized image, respectively, the colored parts of the main and secondary fire lines are merged to obtain a corresponding merged image. Specifically, after the segmentation is completed, the obtained binary image is ANDed with its initial temperature field. In this way, the actual temperature measurement value will be filled in the segmented area, and at the same time, the black part will be filled with null values. The filled image is recorded as T im , for the convenience of subsequent calculations. Among them, T imThe calculation of is as follows:

[0066] ;

[0067] Wherein, t(i, j) is the temperature value of the corresponding pixel point in the filled image.

[0068] Combination Figure 3 As shown in the figure, the original image is clearly segmented, and the traditional coloring is uniformly colored from the minimum value to the maximum value, which greatly affects the intuitive feeling. In addition, since the temperature value is much larger than the maximum color gamut of the image (255), special processing should be performed. Therefore, this solution uses two fire lines (also known as fire lines) for segmentation (main / secondary fire lines), which can further improve the control decision. Specifically, combined with Figure 4 As shown, first normalization is performed, wherein the normalization range of the main fire line is 125-255, and the normalization range of the secondary fire line is 0-125; then the segmented area corresponding to the main fire line is colored; then the segmented area corresponding to the secondary fire line is colored; finally, the colored parts of the main / secondary fire lines are merged to obtain the merged image. In this way, the segmentation margin line can be seen more clearly, and the boundary between the main and secondary fire lines is clear.

[0069] Regarding the camera's dust detection, in this embodiment, the dust detection of the camera device based on the preset dust detection rules and the segmented image includes: determining the corresponding dust detection area from the merged image based on the preset area demarcation rules, and cropping the merged image based on the dust detection area to obtain the corresponding cropped image; performing corresponding image normalization and smoothing filtering on the cropped image in sequence to obtain the corresponding filtered image; using the Sobel operator to determine the gradient information of each pixel in the filtered image in the horizontal and vertical directions, respectively, to obtain the gradient information corresponding to each pixel in the filtered image and the corresponding average gradient information; judging each of the gradient information and the average gradient information based on the preset gradient threshold and the preset average gradient threshold, respectively, to complete the corresponding dust detection using the obtained judgment results. Specifically, 1) define the detection area. In order to avoid the influence of other factors in the image, such as text and other information in the image, the area with clear fire line boundaries should be selected for detection; 2) Image normalization. In order to improve efficiency, the image is normalized; 3) Image filtering. The image is smoothed to avoid the influence of small fires in the image on the image quality; 4) Use the Sobel operator to calculate the gradients in the horizontal and vertical directions respectively; 5) Determine the number of pixels greater than the preset gradient threshold. When the directional gradient is greater than the threshold, the position is determined to be the fire line position; 6) In order to prevent misjudgment, further average the gradient and compare it with the preset average gradient threshold. Combined with Figure 5As shown in the figure, we can clearly see the gradient distribution in the x and y directions, from which we can infer whether there is a line of fire, and further determine whether the camera is clear. The gradient amplitude Grad is calculated according to the formula:

[0070] ;

[0071] Among them, G x 2 , G y 2 Represents the gradient information in the x and y directions respectively. The calculated gradient is closely related to the range of the image value itself. When calculating, a reasonable normalization range should be selected.

[0072] Finally, two hyperparameters are given: the preset image threshold and the preset average gradient threshold. In this application, the Grad determined based on the gradient information is compared with the preset image threshold. When the number of Grads greater than the preset image threshold is greater than n (i.e., the preset number threshold) and the average gradient is greater than the preset average gradient threshold, the camera is determined to be clear. That is, when the obtained detection result shows that the preset camera device is not covered with dust, the preset region of interest is used to draw the fire line of the segmented image to obtain the corresponding drawn image, including: when the judgment result shows that the number currently greater than the preset gradient threshold is greater than the preset number threshold, and the average gradient information is greater than the preset average gradient threshold, a detection result indicating that the preset camera device is not covered with dust is obtained; after determining the preset region of interest in the filtered image based on the preset configuration information and setting the corresponding range for the preset region of interest, the main and secondary fire lines are drawn to obtain the corresponding drawn image.

[0073] Further, combined with Figure 2 As shown, in this embodiment, after the ash falling detection is completed, the denoising algorithm is used to filter out the tiny flame at the end of the combustion. Then the fan area corresponding to the end of the waste incineration combustion is collected (that is, the preset area of ​​interest, which can be customized by the user, that is, Figure 6 and set the range for each area and draw the main and auxiliary fire lines. Figure 6 The preset region of interest (ROI), flame segmentation, and fire line drawing (ROI) are shown. Figure 6 The line below the flame field) and the lowest point of the fire line (that is, the Figure 6 The temperature distribution of the flame field can also be visually judged by color in specific implementation. At the same time, the flame burning state can be observed, and different segmentation results can be obtained by customizing the temperature threshold. It can be understood that the drawing of the main and secondary fire lines is to facilitate the observation of the fire line position.

[0074] Step S14: analyzing the garbage combustion status based on the drawn image, and sending the obtained analysis results including the fire line position to a preset distributed control system, so that the preset distributed control system can adjust the fan frequency based on the analysis results to complete the corresponding combustion control operation.

[0075] Specifically, in this embodiment, the garbage combustion state analysis is performed based on the drawn image, and the obtained analysis results including the position of the fire line are sent to the preset distributed control system, including: determining the corresponding fire line position based on the range information of the preset area of ​​interest in the drawn image, the position information of the lowest point of the fire line, and the height of the drawn image; in the process of using the preset area of ​​interest in the drawn image to perform the corresponding flame area ratio analysis, average temperature analysis, maximum temperature analysis, and minimum temperature analysis, by calculating the area between the main and secondary fire lines to determine whether there is a burnout phenomenon at present, so as to complete the corresponding garbage combustion state analysis operation and obtain the corresponding analysis results; sending the analysis results to the preset distributed control system based on the preset communication protocol. Among them, regarding the position of the lowest point of the fire line:

[0076] ;

[0077] Among them, loc is the position of the fire line; CalculatedPos is the position of the lowest point of the fire line calculated from the image; ImageHeight is the height of the image; Δrange is the defined range difference, that is, the range information of the preset area of ​​interest.

[0078] The ratio of the flame area:

[0079] ;

[0080] Among them, num(T) is the size of the temperature field, num(~T nan ) is the number of non-null values, i.e., the flame field. Similarly, the average temperature, the highest temperature, and the lowest temperature can be directly calculated. It is understandable that the area between the main and secondary fire lines can be calculated by the main and secondary fire lines, and the proportion of the area occupied by the flame can be further calculated, so as to determine whether the burnout phenomenon occurs based on the proportion of the flame, so as to complete the corresponding combustion state analysis.

[0081] Afterwards, ModBus / TCP (ModBus / Transmission Control Protocol, a communication protocol in industrial control systems) protocol is used for communication to transmit the above analysis results to the DCS, and the DCS adjusts the fan frequency based on the received analysis results and the internal state of the waste-to-energy boiler.

[0082] In summary, in this embodiment, auxiliary control of the frequency offset of the fan in the combustion section is realized during garbage incineration, and the automation rate is improved; the problem of temperature measurement in the furnace is solved, and the temperature is measured by combining the camera with Planck's law; the flame combustion state can be effectively divided by temperature field segmentation and fire line position measurement; the problem of camera ash falling is difficult to determine, and the preset ash falling detection rules are used to accurately determine whether the camera of the preset camera device has ash falling; the problem of inaccurate ACC control is solved, and the garbage combustion state is determined according to the analysis results and fed back to the DCS; the deployment and operation cost problem is solved, and the existing camera is reused, and it can be operated without additional configuration. In addition, through custom parameters, different camera positions and resolutions can be adapted.

[0083] It can be seen that in the embodiment of the present application, the furnace of the waste-to-energy boiler is collected in real time by a preset camera device that has completed temperature calibration in advance, and the corresponding furnace monitoring image located at the end of the waste incineration combustion is obtained; based on the Planck blackbody radiation law and the preset temperature threshold, the temperature field calculation and flame segmentation of the furnace monitoring image are respectively performed to obtain the corresponding segmented image; based on the preset ash detection rule and the segmented image, the camera device is detected for ash, and when the obtained detection result shows that the preset camera device has not fallen ash, the segmented image is drawn using the preset region of interest to obtain the corresponding drawn image; based on the drawn image, the garbage combustion state is analyzed, and the obtained analysis result including the position of the fire line is sent to the preset distributed control system, so that the preset distributed control system performs fan frequency regulation based on the analysis result to complete the corresponding combustion control operation. That is, in the present application, the temperature field of the collected image is determined based on the preset camera device that has completed temperature calibration in advance and combined with the Planck blackbody radiation law, so as to determine the corresponding temperature information. Then, based on the preset ash detection rule, it is detected whether the preset camera device has fallen ash. Then, when the ash has not fallen, the garbage combustion state is analyzed by drawing the fire line, and the analysis results are sent to the preset distributed control system so that the preset distributed control system can use the analysis results to control the combustion of the furnace of the garbage power generation boiler. In this way, the fan frequency of the combustion section can be automatically controlled while solving the existing problem of requiring a lot of input from operators, and the accuracy of combustion control can be improved.

[0084] Combine the following Figure 2 , Figure 6-Figure 8 The schematic diagram disclosed in the figure specifically illustrates the technical solution of the embodiment of the present application.

[0085] In this embodiment, a preset camera device that pre-marks the temperature based on artificial or laboratory temperature is used to collect images in real time and save them in the form of video. Then, the temperature field is calculated and the image is segmented using Planck's law to determine the corresponding flame field based on the segmented image.

[0086] After that, the segmented image is cropped to crop the area to be detected, and normalization and image filtering are performed in sequence. After filtering, the gradients of each pixel in the image in the horizontal and vertical directions are calculated, and the squared gradient difference and the average gradient corresponding to the image are calculated. Then the obtained squared gradient difference and the average gradient are threshold judged respectively. Only when the number greater than the preset gradient threshold is greater than the preset number threshold, and the average gradient information is greater than the preset average gradient threshold, it indicates that there is no dust (that is, it is covered with dust), otherwise it is determined that the camera of the preset camera device is covered with dust.

[0087] It is understandable that if it is determined that ash has fallen, it will take a certain time interval (the time to process the ash) before resuming image acquisition. If it is determined that ash has not fallen, the main and auxiliary fire lines are drawn, and the small flame at the end of the combustion is filtered out using a denoising algorithm. After that, analysis is performed based on the ROI area, and smoothing filtering is performed to avoid fluctuations in the analysis results due to ash falling. Finally, the analysis results are sent to the DCS for control.

[0088] Specifically, when the fire line position drops, it means that the garbage is not fully burned and needs to be burned before reaching the ember stage, so the fan frequency offset needs to be increased. When the fire line rises, it means that the garbage is fully burned and the fan frequency offset should be appropriately reduced. Figure 8 The change between the fire line position and the fan frequency is shown. It can be seen from the figure that when the fire line position drops, the garbage needs to be fully burned; at this time, although the fire line rises, the rise is relatively slow, so the fan frequency continues to increase to ensure that it is burned before the ember stage. Therefore, it can be concluded that the fan control can be effectively and accurately realized by using the fire line position analyzed from the image. In addition, through page configuration, multiple positions in the furnace can be monitored at the same time, and the frequency of multiple fans can be controlled at the same time.

[0089] See also Fig. 9 As shown, the embodiment of the present application also discloses a garbage power generation boiler combustion control device, including:

[0090] The image acquisition module 11 is used to acquire real-time images of the furnace of the waste-to-energy boiler through a preset camera device that has completed temperature calibration in advance, and obtain a corresponding monitoring image of the furnace located at the end of the waste incineration combustion;

[0091] The segmented image acquisition module 12 is used to perform temperature field calculation and flame segmentation on the furnace monitoring image based on Planck's blackbody radiation law and a preset temperature threshold to obtain a corresponding segmented image;

[0092] A dust detection module 13 is used to perform dust detection on the camera device based on a preset dust detection rule and the segmented image, and when the obtained detection result indicates that the preset camera device is not dusted, perform line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image;

[0093] The combustion control module 14 is used to analyze the garbage combustion status based on the drawn image, and send the obtained analysis results including the fire line position to a preset distributed control system, so that the preset distributed control system can adjust the fan frequency based on the analysis results to complete the corresponding combustion control operation.

[0094] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0095] It can be seen that in the present application, the temperature field of the captured image is determined based on the preset camera device that has completed the temperature calibration in advance and combined with Planck's blackbody radiation law, so as to determine the corresponding temperature information. Afterwards, the preset camera device is detected to see whether there is ash falling based on the preset ash falling detection rules. Then, when there is no ash falling, the garbage combustion state is analyzed by drawing a fire line, and the analysis results are sent to the preset distributed control system, so that the preset distributed control system can use the analysis results to control the combustion of the furnace of the garbage power generation boiler. In this way, the automatic control of the fan frequency of the combustion section can be achieved while solving the existing problem that requires a lot of input from operators, and the accuracy of combustion control is improved.

[0096] In some specific embodiments, the image acquisition module 11 may specifically include:

[0097] The monitoring image acquisition unit is used to collect real-time images of the furnace of the waste-to-energy boiler through a preset camera device that has been temperature-calibrated in advance using Planck's blackbody radiation law, and obtain corresponding furnace monitoring images located at the end of the waste incineration combustion.

[0098] In some specific embodiments, the segmented image acquisition module 12 may specifically include:

[0099] An initial temperature field determination unit, used to determine an initial temperature field corresponding to the furnace monitoring image based on Planck's blackbody radiation law; wherein the initial temperature field includes the temperature value of each pixel point in the furnace monitoring image;

[0100] The segmented image acquisition unit is used to compare each of the temperature values ​​with a preset temperature threshold, and perform segmentation using the comparison results corresponding to each of the pixels, so as to obtain a binary image as the segmented image.

[0101] In some specific embodiments, the garbage power generation boiler combustion control device may further include:

[0102] A filled image acquisition unit, used for performing a AND operation on the segmented image and the initial temperature field, and performing null value filling on the black part to obtain a corresponding filled image;

[0103] A normalization unit, used for normalizing the temperature information in the filled image based on a preset main fire line normalization range and a preset auxiliary fire line normalization range to obtain a corresponding normalized image;

[0104] The coloring and merging unit is used to merge the colored parts of the main and secondary fire lines after coloring the segmented areas corresponding to the main fire line and the secondary fire line in the normalized image, so as to obtain the corresponding merged image.

[0105] In some specific embodiments, the dust falling detection module 13 may specifically include:

[0106] An image cropping unit, configured to determine a corresponding dust detection area from the merged image based on a preset area demarcation rule, and crop the merged image based on the dust detection area to obtain a corresponding cropped image;

[0107] A filtered image acquisition unit, used to perform corresponding image normalization and smoothing filtering on the cropped image in sequence to obtain a corresponding filtered image;

[0108] A gradient determination unit, used to determine the gradient information of each pixel point in the filtered image in the horizontal and vertical directions by using a Sobel operator, so as to obtain the gradient information corresponding to each pixel point in the filtered image and the corresponding average gradient information;

[0109] The threshold judgment unit is used to judge each of the gradient information and the average gradient information based on a preset gradient threshold and a preset average gradient threshold, respectively, so as to complete the corresponding dust falling detection using the obtained judgment result.

[0110] In some specific embodiments, the dust falling detection module 13 may specifically include:

[0111] A detection result obtaining unit, configured to obtain a detection result indicating that the preset camera device is not dusty when the judgment result indicates that the number currently greater than the preset gradient threshold is greater than the preset number threshold, and the average gradient information is greater than the preset average gradient threshold;

[0112] The fire line drawing unit is used to draw the main and auxiliary fire lines after determining the preset region of interest in the filtered image based on the preset configuration information and setting the corresponding range for the preset region of interest to obtain the corresponding drawn image.

[0113] In some specific embodiments, the combustion control module 14 may specifically include:

[0114] A firing line position determining unit, configured to determine a corresponding firing line position based on the range information of the preset region of interest in the drawn image, the position information of the lowest point of the firing line, and the height of the drawn image;

[0115] An analysis result acquisition unit is used to determine whether there is a burnout phenomenon by calculating the area between the main and auxiliary fire lines in the process of performing corresponding flame area ratio analysis, average temperature analysis, maximum temperature analysis, and minimum temperature analysis using the preset area of ​​interest in the drawn image, so as to complete the corresponding garbage combustion state analysis operation and obtain the corresponding analysis result;

[0116] The result generating unit is used to send the analysis result to a preset distributed control system based on a preset communication protocol.

[0117] Furthermore, the present application also discloses an electronic device. Fig.10 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0118] Fig.10 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the waste-to-energy boiler combustion control method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0119] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0120] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0121] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the garbage power generation boiler combustion control method executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0122] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned waste-to-energy boiler combustion control method is implemented. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0123] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0124] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0125] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0126] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0127] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for controlling combustion of a waste-to-energy boiler, characterized in that: include: The furnace of the waste-to-energy boiler is captured in real time by a preset camera device that has been temperature-calibrated in advance, and a corresponding monitoring image of the furnace located at the end of the waste incineration combustion is obtained; Based on Planck's blackbody radiation law and a preset temperature threshold, temperature field calculation and flame segmentation are performed on the furnace monitoring image to obtain a corresponding segmented image; Perform dust detection on the camera device based on a preset dust detection rule and the segmented image, and when the obtained detection result indicates that the preset camera device is not dusted, perform line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image; The garbage combustion state is analyzed based on the drawn image, and the obtained analysis results including the fire line position are sent to a preset distributed control system so that the preset distributed control system can adjust the fan frequency based on the analysis results to complete the corresponding combustion control operation.

2. The waste-to-energy boiler combustion control method according to claim 1, characterized in that: The preset camera device that has completed temperature calibration in advance performs real-time image acquisition on the furnace of the waste-to-energy boiler to obtain the corresponding furnace monitoring image located at the end of the waste incineration combustion, including: The furnace of the waste-to-energy boiler is imaged in real time by using a preset camera device that has been temperature calibrated in advance using Planck's blackbody radiation law, thereby obtaining a corresponding monitoring image of the furnace at the final stage of waste incineration.

3. The waste-to-energy boiler combustion control method according to claim 1, characterized in that: The temperature field calculation and flame segmentation of the furnace monitoring image are performed based on Planck's blackbody radiation law and a preset temperature threshold to obtain a corresponding segmented image, including: Determine an initial temperature field corresponding to the furnace monitoring image based on Planck's blackbody radiation law; wherein the initial temperature field includes the temperature value of each pixel in the furnace monitoring image; Each of the temperature values ​​is compared with a preset temperature threshold, and segmentation is performed using the comparison results corresponding to each of the pixels, so as to obtain a binary image as a segmented image.

4. The waste-to-energy boiler combustion control method according to claim 3, characterized in that: Before performing dust detection on the camera device based on the preset dust detection rule and the segmented image, the method further includes: Performing a union operation on the segmented image and the initial temperature field, and filling the black part with null values ​​to obtain a corresponding filled image; Normalizing the temperature information in the filled image based on a preset main fire line normalization range and a preset secondary fire line normalization range to obtain a corresponding normalized image; After coloring the segmented areas corresponding to the main fire line and the secondary fire line in the normalized image, the colored parts of the main fire line and the secondary fire line are merged to obtain a corresponding merged image.

5. The waste-to-energy boiler combustion control method according to claim 4, characterized in that: The dust detection of the camera device based on the preset dust detection rule and the segmented image includes: Determining a corresponding dust falling detection area from the merged image based on a preset area demarcation rule, and cropping the merged image based on the dust falling detection area to obtain a corresponding cropped image; Performing corresponding image normalization and smoothing filtering on the cropped image in sequence to obtain a corresponding filtered image; Determine the gradient information of each pixel point in the filtered image in the horizontal and vertical directions by using the Sobel operator to obtain the gradient information corresponding to each pixel point in the filtered image and the corresponding average gradient information; The gradient information and the average gradient information are judged based on the preset gradient threshold and the preset average gradient threshold respectively, so as to complete the corresponding dust falling detection using the obtained judgment results.

6. The waste-to-energy boiler combustion control method according to claim 5, characterized in that: When the obtained detection result indicates that the preset camera device is not covered with dust, the segmented image is subjected to line drawing using a preset region of interest to obtain a corresponding drawn image, including: When the judgment result indicates that the number currently greater than the preset gradient threshold is greater than the preset number threshold, and the average gradient information is greater than the preset average gradient threshold, a detection result indicating that the preset camera device is not dusty is obtained; After determining a preset region of interest in the filtered image based on preset configuration information and setting a corresponding range for the preset region of interest, primary and secondary fire line drawing is performed to obtain a corresponding drawn image.

7. The waste-to-energy boiler combustion control method according to any one of claims 1 to 6, characterized in that: The garbage combustion state analysis is performed based on the drawn image, and the obtained analysis result including the fire line position is sent to a preset distributed control system, including: Determine the corresponding firing line position based on the range information of the preset region of interest in the drawn image, the position information of the lowest point of the firing line, and the height of the drawn image; In the process of performing corresponding flame area ratio analysis, average temperature analysis, maximum temperature analysis, and minimum temperature analysis using the preset region of interest in the drawn image, it is determined whether there is currently a burnout phenomenon by calculating the area between the main and auxiliary fire lines, so as to complete the corresponding garbage combustion state analysis operation and obtain the corresponding analysis results; The analysis result is sent to a preset distributed control system based on a preset communication protocol.

8. A garbage power generation boiler combustion control device, characterized in that: include: An image acquisition module is used to acquire real-time images of the furnace of the waste-to-energy boiler through a preset camera device that has completed temperature calibration in advance, and obtain a corresponding monitoring image of the furnace located at the end of the waste incineration combustion; A segmented image acquisition module is used to perform temperature field calculation and flame segmentation on the furnace monitoring image based on Planck's blackbody radiation law and a preset temperature threshold to obtain a corresponding segmented image; A dust falling detection module is used to perform dust falling detection on the camera device based on a preset dust falling detection rule and the segmented image, and when the obtained detection result indicates that the preset camera device is not dusted, perform line drawing on the segmented image using a preset region of interest to obtain a corresponding drawn image; The combustion control module is used to analyze the garbage combustion status based on the drawn image, and send the obtained analysis results including the fire line position to a preset distributed control system, so that the preset distributed control system can adjust the fan frequency based on the analysis results to complete the corresponding combustion control operation.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the waste-to-energy boiler combustion control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the waste-to-energy boiler combustion control method as described in any one of claims 1 to 7.

Images