Power plant boiler control method and system

Abstract

The invention relates to a power plant boiler control method and system, and belongs to the technical field of thermal power generation methods and equipment. According to the technical scheme, when the load change rate of the boiler is larger than a first threshold value, a first control model is determined as a target control model; in response to the fact that the load change rate of the boiler is smaller than or equal to a first threshold value, the second control model is determined as a target control model, and the precision of the first control model is smaller than that of the second control model; inputting combustion parameters of the boiler into the target control model to obtain an air-coal ratio; and performing combustion control on the boiler based on the air-coal ratio. The method has the beneficial effects that different control models are dynamically selected according to the load change rate of the boiler, different working conditions can be better adapted, and the stability and the high efficiency of boiler operation are both considered.

Description

Technical Field

[0001] The present invention relates to a power plant boiler control method and system, belonging to the technical field of thermal power generation methods and equipment. Background Art

[0002] A power plant boiler is a key component of thermal power stations. It uses its heating surface to transfer heat energy generated by fuel combustion to a working medium (usually water). As the water flows through the boiler's heating surface pipes, it absorbs heat, gradually heating up and vaporizing, ultimately turning into high-temperature, high-pressure steam. Steam is then drawn from the boiler's steam outlet and piped to the steam turbine. Inside the turbine, the high-speed steam strikes the turbine blades, rotating the turbine rotor and generating electricity.

[0003] In boiler control systems, the air-to-fuel ratio is a key parameter for combustion control. A reasonable air-to-fuel ratio ensures complete fuel combustion, maintaining stable boiler operation and high performance. Existing air-to-fuel ratio control methods often employ simple boiler control strategies, which can easily lead to incomplete combustion and low fuel efficiency. Summary of the Invention

[0004] The purpose of the present invention is to provide a power plant boiler control method and system, which dynamically selects different control models according to the load change rate of the boiler, so that the boiler can quickly adjust the combustion intensity to adapt to the increase or decrease of the load when it is in the stage of rapid load increase or decrease; when the load change rate is small, the combustion parameters are accurately adjusted, the combustion process is optimized, and the energy utilization efficiency is improved; it can better adapt to different working conditions, take into account the stability and efficiency of the boiler operation, and effectively solve the above-mentioned problems existing in the background technology.

[0005] The technical solution of the present invention is: a power plant boiler control method, comprising the following steps:

[0006] S101: In response to a boiler load change rate being greater than a first threshold, determining a first control model as a target control model;

[0007] S102: In response to the boiler load change rate being less than or equal to a first threshold, determining the second control model as the target control model, and the accuracy of the first control model is less than the accuracy of the second control model;

[0008] S103, inputting the boiler combustion parameters into the target control model to obtain the air-coal ratio;

[0009] S104. Control the combustion of the boiler based on the air-coal ratio.

[0010] The first control model and the second control model are both multi-layer perceptron models, and the number of hidden layers in the first control model is smaller than the number of hidden layers in the second control model.

[0011] In step S103, the combustion parameters include the flame intensity and flame shape of the burner, and the specific steps are as follows:

[0012] performing grayscale processing on the first flame image to obtain a second flame image;

[0013] extracting an edge contour of the flame area from the second flame image;

[0014] determining the flame intensity based on the grayscale value of the flame area;

[0015] The flame shape is determined based on the edge contour of the flame area.

[0016] The step of extracting the edge contour of the flame area from the second flame image includes:

[0017] Obtaining the first edge of the flame area based on the edge detection algorithm;

[0018] The first edge is sequentially subjected to dilation and erosion operations to obtain an edge contour of the flame region.

[0019] The step of sequentially performing an expansion operation and an erosion operation on the first edge to obtain an edge contour of the flame area includes:

[0020] determining a shape of the structural element based on a noise distribution of the second flame image;

[0021] determining a size of the structural element based on a noise size of the second flame image;

[0022] Based on the structure element, the dilation operation and the erosion operation are sequentially performed on the first edge to obtain the edge contour of the flame area.

[0023] The determining the shape of the structural element based on the noise distribution of the second flame image comprises:

[0024] Calculating a first difference in grayscale value between each pixel and adjacent pixels in the second flame image;

[0025] In response to the proportion of first pixels in the second flame image being less than or equal to a second threshold, determining the shape of the structural element as a circle; the first pixel being a pixel for which the sum of the absolute values of the corresponding plurality of first differences is greater than a third threshold;

[0026] In response to the proportion of the first pixel points in the second flame image being greater than a second threshold, the shape of the structural element is determined to be a cross.

[0027] It also includes the following steps:

[0028] In response to a load change rate of the boiler being greater than a first threshold, adjusting the water inlet flow rate of the boiler with a first cycle;

[0029] In response to the load change rate of the boiler being less than or equal to a first threshold, the water inlet flow of the boiler is adjusted with a second period; the first period is less than the second period.

[0030] A power plant boiler control system includes a first processing module, a second processing module, a first calculation module and a first control module, wherein the first processing module and the second processing module respectively carry a first control model and a second control model, the first processing module and the second processing module are connected to the first calculation module, and the first calculation module is connected to the first control module.

[0031] An electronic device comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory and runs on the processor, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

[0033] The beneficial effects of the present invention are: by dynamically selecting different control models according to the load change rate of the boiler, the boiler can quickly adjust the combustion intensity to adapt to the increase or decrease of the load when it is in the stage of rapid load increase or load decrease; when the load change rate is small, the combustion parameters are accurately adjusted, the combustion process is optimized, and the energy utilization efficiency is improved; it can better adapt to different working conditions and take into account the stability and efficiency of the boiler operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0035] Figure 2 is a flow chart of the method of the present invention;

[0036] Figure 3 is a block diagram of an electronic device of the present invention;

[0037] In the figure: a power plant boiler control system 20, a first processing module 21, a second processing module 22, a first calculation module 23, a first control module 24, an electronic device 300, a processor 301, an input device 302, an output device 303, a memory 304, and a communication bus 305. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the invention implementation cases clearer, the technical solutions in the invention implementation cases will be clearly and completely described below in conjunction with the drawings in the implementation cases. Obviously, the implementation cases described are only a small part of the implementation cases of the present invention, rather than all the implementation cases. Based on the implementation cases in the present invention, all other implementation cases obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0039] A power plant boiler control method comprises the following steps:

[0040] S101: In response to a boiler load change rate being greater than a first threshold, determining a first control model as a target control model;

[0041] S102: In response to the boiler load change rate being less than or equal to a first threshold, determining the second control model as the target control model, and the accuracy of the first control model is less than the accuracy of the second control model;

[0042] S103, inputting the boiler combustion parameters into the target control model to obtain the air-coal ratio;

[0043] S104. Control the combustion of the boiler based on the air-coal ratio.

[0044] The first control model and the second control model are both multi-layer perceptron models, and the number of hidden layers in the first control model is smaller than the number of hidden layers in the second control model.

[0045] In step S103, the combustion parameters include the flame intensity and flame shape of the burner, and the specific steps are as follows:

[0046] performing grayscale processing on the first flame image to obtain a second flame image;

[0047] extracting an edge contour of the flame area from the second flame image;

[0048] determining the flame intensity based on the grayscale value of the flame area;

[0049] The flame shape is determined based on the edge contour of the flame area.

[0050] The step of extracting the edge contour of the flame area from the second flame image includes:

[0051] Obtaining the first edge of the flame area based on the edge detection algorithm;

[0052] The first edge is sequentially subjected to dilation and erosion operations to obtain an edge contour of the flame region.

[0053] The step of sequentially performing an expansion operation and an erosion operation on the first edge to obtain an edge contour of the flame area includes:

[0054] determining a shape of the structural element based on a noise distribution of the second flame image;

[0055] determining a size of the structural element based on a noise size of the second flame image;

[0056] Based on the structure element, the dilation operation and the erosion operation are sequentially performed on the first edge to obtain the edge contour of the flame area.

[0057] The determining the shape of the structural element based on the noise distribution of the second flame image comprises:

[0058] Calculating a first difference in grayscale value between each pixel and adjacent pixels in the second flame image;

[0059] In response to the proportion of first pixels in the second flame image being less than or equal to a second threshold, determining the shape of the structural element as a circle; the first pixel being a pixel for which the sum of the absolute values of the corresponding plurality of first differences is greater than a third threshold;

[0060] In response to the proportion of the first pixel points in the second flame image being greater than a second threshold, the shape of the structural element is determined to be a cross.

[0061] It also includes the following steps:

[0062] In response to the boiler load change rate being greater than a first threshold, the boiler water inlet flow is adjusted with a first cycle; in response to the boiler load change rate being less than or equal to the first threshold, the boiler water inlet flow is adjusted with a second cycle; the first cycle is less than the second cycle.

[0063] A power plant boiler control system includes a first processing module 21, a second processing module 22, a first calculation module 23 and a first control module 24. The first processing module 21 and the second processing module 22 respectively carry a first control model and a second control model. The first processing module 21 and the second processing module 22 are connected to the first calculation module 23, and the first calculation module 23 is connected to the first control module 24.

[0064] An electronic device comprises a memory 304, a processor 301 and a computer program, wherein the computer program is stored in the memory 304 and runs on the processor 301, and when the processor 301 executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

[0065] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

[0066] In practical applications, the method of the present invention comprises the following steps:

[0067] S101 : In response to a load change rate of a boiler being greater than a first threshold, determining a first control model as a target control model.

[0068] In this embodiment, the first control model can be constructed based on fuzzy control logic or a neural network model. Specifically, a model with a smaller computational load can be used to avoid slow model response speed caused by excessive computational load.

[0069] When the load change rate of the boiler is greater than the first threshold, it indicates that the operating conditions of the boiler have changed dramatically. For example, during the peak regulation period of the power grid, the generator set needs to respond quickly to the load change. At this time, the air-coal ratio is calculated based on the first control model, which allows the boiler to quickly adjust the combustion intensity to adapt to the increase and decrease of the load.

[0070] S102: In response to the boiler load change rate being less than or equal to a first threshold, determining the second control model as the target control model; the accuracy of the first control model is less than the accuracy of the second control model.

[0071] In this embodiment, the second control model can be constructed based on fuzzy control logic or a neural network model, and the accuracy of the second control model is higher than that of the first control model.

[0072] When the load change rate is small, it indicates that the boiler operating condition is relatively stable. At this time, selecting the second control model with higher accuracy can more accurately adjust the combustion parameters, optimize the combustion process, and improve energy utilization efficiency.

[0073] S103: Input the boiler's combustion parameters into the target control model to obtain the air-coal ratio.

[0074] In this embodiment, the air-to-fuel ratio refers to the ratio between the amount of air and fuel entering the boiler during the combustion process. Combustion parameters may include fuel quantity, air flow rate, flame intensity, flame shape, flue gas temperature, oxygen content, carbon monoxide, and carbon dioxide content.

[0075] When the air-to-fuel ratio is appropriate, the fuel can burn fully and stably, and the flame intensity is moderate and stable. When the air-to-fuel ratio is unbalanced, such as when the air volume is insufficient or the air-to-fuel ratio is too low, the fuel will not burn fully and the flame intensity will weaken. When the air volume is too large or the air-to-fuel ratio is too high, the flame may be blown away, and the heat will be carried away by the excess air, which will also reduce the flame intensity.

[0076] At the same time, when the air-to-coal ratio is appropriate, the fuel burns fully, the carbon dioxide content is relatively high, the carbon monoxide content is low, the released heat can be effectively transferred to the heating surface, and the flue gas temperature is within a reasonable range. When the air-to-coal ratio is too low, the fuel burns incompletely, the heat generated is reduced, the flue gas temperature will drop, and the carbon monoxide content will increase; when the air-to-coal ratio is too high, the excess air absorbs too much heat, which will also lower the flue gas temperature and increase exhaust heat loss; and the carbon dioxide content is abnormally low, indicating that the air-to-coal ratio is too high and a large amount of air has diluted the carbon dioxide concentration in the combustion products.

[0077] Furthermore, the oxygen content in flue gas can also reflect the air-to-fuel ratio. Excessive oxygen levels indicate an excessive air-to-fuel ratio, meaning too much air is being introduced. Low oxygen levels indicate an insufficient air-to-fuel ratio, potentially leading to incomplete combustion of the fuel. By monitoring flue gas oxygen levels, the air-to-fuel ratio can be adjusted in real time to achieve optimal combustion.

[0078] Therefore, the first control model and the second control model can be pre-trained based on the historical data of the above-mentioned combustion parameters and air-coal ratio, and the trained first control model or the second control model can be used in the control of the air-coal ratio to automatically adjust the air-coal ratio according to changes in the combustion parameters and improve the combustion efficiency.

[0079] S104: Control the combustion of the boiler based on the air-coal ratio.

[0080] In this embodiment, after obtaining a suitable air-coal ratio, the blower, coal feeder and other equipment can be adjusted based on the air-coal ratio to control the air volume and coal volume entering the boiler so that the actual air-coal ratio reaches the target value, thereby achieving effective control of the boiler combustion process and optimizing the combustion effect.

[0081] From the above, it can be concluded that in this embodiment, when the load change rate of the boiler is greater than the first threshold, the first control model is selected to calculate the air-coal ratio, which can enable the boiler to quickly adjust the combustion intensity to adapt to the increase and decrease of the load; when the load change rate is small, it indicates that the boiler operating condition is relatively stable. At this time, the second control model with higher accuracy is selected, which can more accurately adjust the combustion parameters, optimize the combustion process, and improve energy utilization efficiency.

[0082] This embodiment dynamically selects different control models according to the load change rate of the boiler, which can better adapt to different working conditions and take into account the stability and efficiency of the boiler operation.

[0083] In one embodiment of the present disclosure, the first control model and the second control model are both multilayer perceptron models, and the number of hidden layers of the first control model is smaller than the number of hidden layers of the second control model.

[0084] In this embodiment, during boiler combustion, a complex nonlinear relationship exists between the air-to-fuel ratio and combustion parameters (such as fuel quantity, air supply, flame intensity, flue gas temperature, and oxygen content). The multi-layer perceptron model has multiple hidden layers, each containing multiple neurons. These neurons operate using nonlinear activation functions (such as Sigmoid and ReLU). This can effectively fit the complex nonlinear mapping relationship between the air-to-fuel ratio and various combustion parameters, achieving precise control of the air-to-fuel ratio.

[0085] Setting a smaller number of hidden layers in the first control model can make the calculation complexity of the first control model low and the calculation speed fast. When the boiler load change rate is greater than the first threshold and the operating conditions change drastically, the input combustion parameters can be processed quickly and the air-coal ratio can be adjusted quickly.

[0086] Setting a larger number of hidden layers in the second control model can make the second control model have stronger nonlinear fitting ability. When the boiler load change rate is less than or equal to the first threshold and the operating conditions are stable, the complex nonlinear relationship between the combustion parameters and the air-coal ratio can be more accurately captured, thereby more accurately calculating the optimal air-coal ratio, achieving more refined combustion control, improving energy utilization efficiency, and reducing pollutant emissions.

[0087] In one embodiment of the present disclosure, the combustion parameters include the flame intensity and flame shape of the burner, and the power plant boiler control method further includes:

[0088] performing grayscale processing on the first flame image to obtain a second flame image;

[0089] extracting an edge contour of the flame area from the second flame image;

[0090] determining the flame intensity based on the grayscale value of the flame area;

[0091] The flame shape is determined based on the edge contour of the flame area.

[0092] In this embodiment, an image acquisition device may be provided at the observation port of the combustion chamber to acquire flame images (ie, first flame images) in real time, and the flame intensity and flame shape may be obtained by analyzing the first flame images.

[0093] Specifically, the first flame image can be grayscale processed to remove color information, thereby reducing the amount of data and making subsequent extraction and analysis of the flame region more efficient. A commonly used edge detection algorithm (such as the Canny operator) is then used to extract the edge contours of the flame region. By statistically analyzing the grayscale distribution within the flame region, the flame intensity can be quantitatively determined. For example, the average grayscale value of the flame region can be calculated.

[0094] Based on the edge contours of the flame area, a series of geometric analysis methods can be used to determine the flame shape. For example, the perimeter, area, aspect ratio, and other parameters of the contour can be calculated. Accurately determining the flame shape helps determine whether the combustion is normal. For example, a normal flame shape should be relatively regular and stable. If the flame shape is distorted, elongated, or otherwise abnormal, it may indicate a problem with the combustion process, such as a burner failure or an imbalance in the air-to-fuel ratio.

[0095] It can be concluded from the above that this embodiment can obtain flame intensity and shape information in real time by processing and analyzing flame images, providing a more accurate basis for combustion control.

[0096] In one embodiment of the present disclosure, extracting the edge contour of the flame region from the second flame image includes:

[0097] Obtaining the first edge of the flame area based on the edge detection algorithm;

[0098] The first edge is sequentially subjected to dilation and erosion operations to obtain an edge contour of the flame region.

[0099] In this embodiment, it is considered that the flame image itself has strong noise, such as slight fluctuations in ambient light, radiation fluctuations of the flame itself, airflow disturbances during the combustion process, splashing of burning materials, etc., which may cause false edges to appear after edge detection or blur the real edges, affecting the accuracy of detection.

[0100] To solve the above problem, the background points that touch the edge of the flame area are first merged into the flame area through the expansion operation, so that the boundary of the flame area expands outward. For small breaks or discontinuities in the first edge caused by noise or other reasons, the expansion operation can connect these disconnected edges to make the flame edge more coherent. At the same time, it can also enhance some weaker edge signals to make the overall shape of the flame outline more complete.

[0101] While the dilation operation improves edge continuity, it may introduce noise points that don't represent the true flame edge or make the edge too thick. Therefore, an erosion operation is needed to remove these points from the object's edge, shrinking the object's boundary inward. Erosion removes these extraneous points, refines the edge, and makes the flame outline more accurately reflect the true flame boundary, eliminating the overexpansion problem that may occur with the dilation operation and further improving the accuracy and refinement of the outline.

[0102] From the above, it can be concluded that this embodiment can effectively remove noise interference and repair edge incompleteness by combining the edge detection algorithm with dilation and erosion operations, thereby obtaining an edge contour that is more accurate and closer to the actual flame shape, providing a reliable data basis for subsequent analysis and judgment based on the flame shape.

[0103] In one embodiment of the present disclosure, the expansion operation and the erosion operation are sequentially performed on the first edge to obtain the edge profile of the flame area, including:

[0104] determining a shape of the structural element based on a noise distribution of the second flame image;

[0105] determining a size of the structural element based on a noise size of the second flame image;

[0106] Based on the structure element, the dilation operation and the erosion operation are sequentially performed on the first edge to obtain the edge contour of the flame area.

[0107] In this embodiment, the structuring element is the basic unit used for convolution with the image during dilation and erosion operations. If the noise distribution exhibits certain directionality or irregularity, selecting a structuring element shape that matches this can more effectively process the noise. For example, if the noise is more distributed horizontally and vertically, a rectangular structuring element can be selected; if the noise distribution is relatively uniform and has no obvious directional characteristics, a circular structuring element is more effective.

[0108] At the same time, the noise level determines the scope of the structuring element. When the noise is high, a larger structuring element is needed for dilation and erosion operations to more comprehensively cover the noisy area and effectively remove the noise. This is because a larger structuring element can merge more noise points with surrounding normal pixels during dilation, and can more thoroughly remove isolated noise points during erosion. Conversely, when the noise is low, a smaller structuring element can better preserve the details of the flame edge while removing noise, avoiding excessive erosion or expansion of the flame edge due to overly large structuring elements, which can cause edge distortion.

[0109] It can be concluded from the above that this embodiment automatically adjusts the shape and size of the structural element according to the actual distribution and size of the noise in the second flame image, which can improve the effects of the expansion and erosion operations, thereby improving the accuracy and reliability of the flame edge contour extraction.

[0110] In one embodiment of the present disclosure, determining the shape of the structural element based on the noise distribution of the second flame image includes:

[0111] Calculating a first difference in grayscale value between each pixel and adjacent pixels in the second flame image;

[0112] In response to the proportion of first pixels in the second flame image being less than or equal to a second threshold, determining the shape of the structural element as a circle; the first pixel being a pixel for which the sum of the absolute values of the corresponding plurality of first differences is greater than a third threshold;

[0113] In response to the proportion of the first pixel points in the second flame image being greater than a second threshold, the shape of the structural element is determined to be a cross.

[0114] In this embodiment, it is considered that the noise in the flame image is mainly Gaussian noise and salt and pepper noise. When the flame combustion is relatively stable without obvious particle splashing, flickering or other drastic physical changes, small random changes in the intensity of the flame radiation light will generate Gaussian noise. When solid particles are splashed during the flame combustion process or there are impurities in the burning material, these particles or impurities may appear as salt and pepper noise in the image.

[0115] Therefore, this embodiment first determines the main noise distribution in the second flame image based on the analysis of the pixels in the second flame image, and then determines the shape of the structural element based on the main noise distribution.

[0116] Specifically, for each pixel in the second flame image, calculate the sum of the absolute values of the grayscale value differences between it and the surrounding pixels (for example, a 3×3 or 5×5 neighborhood can be selected). Let the image be I, the pixel (x, y), and its 3×3 neighborhood pixels be I ij , i = x-1, x, x+1, j = y-1, y, y+1, calculate the sum of the absolute values of the first differences s as:

[0117]

[0118] If the statistical value s corresponding to most pixels is small, that is, the proportion of the first pixel points is less than or equal to the second threshold, it indicates that the difference between the pixels is not large, mainly Gaussian noise, without obvious directionality and aggregation, and the probability of each pixel being affected by noise is roughly the same, and a circular structuring element can be selected; if the statistical value s corresponding to many pixels is very large, that is, the proportion of the first pixel points is greater than the second threshold, it indicates that there are many points that are very different from the surrounding pixels, mainly salt and pepper noise, which may be relatively concentrated in the horizontal or vertical direction. Using a cross-shaped structuring element can more specifically process the noise points in these directions.

[0119] From the above, it can be concluded that this embodiment specifically selects the appropriate structural element shape based on the actual distribution characteristics of the noise in the image. While removing noise, it can protect the detailed information and original shape of the flame area to the greatest extent, providing a more accurate data basis for subsequent analysis based on flame shape and edges.

[0120] In one embodiment of the present disclosure, the power plant boiler control method further includes:

[0121] In response to the proportion of the first pixel points in the second flame image being less than or equal to a second threshold, calculating a standard deviation of the grayscale value of each pixel point in the second flame image, and determining a noise level of the second flame image based on the standard deviation;

[0122] In response to the proportion of the first pixel points in the second flame image being greater than the second threshold, the noise level of the second flame image is determined based on the proportion of the noise points in the second flame image.

[0123] In this embodiment, when the proportion of the first pixel in the second flame image is less than or equal to the second threshold, it indicates that the second flame image is primarily Gaussian noise. The magnitude of the noise can be determined based on the standard deviation of the grayscale values of each pixel in the second flame image. A larger standard deviation indicates a greater noise intensity. In an ideal noise-free image, the grayscale values of the pixels are relatively stable and the standard deviation is small.

[0124] When the proportion of the first pixel in the second flame image is greater than the second threshold, it indicates that the second flame image is mainly composed of salt and pepper noise. The proportion of pixels that are obviously noise (i.e., white or black dots in salt and pepper noise) in the second flame image to the total pixels can be counted. For example, if the total number of pixels in the image is N and the number of noise points detected is n, the proportion of noise points can be calculated. To express the noise intensity, the greater the proportion of noise points, the greater the intensity of salt and pepper noise.

[0125] It can be concluded from the above that this embodiment determines the corresponding noise intensity calculation method based on the characteristics of Gaussian noise and salt and pepper noise, which is conducive to achieving accurate calculation of noise intensity.

[0126] In one embodiment of the present disclosure, the power plant boiler control method further includes:

[0127] In response to a load change rate of the boiler being greater than a first threshold, adjusting the water inlet flow rate of the boiler with a first cycle;

[0128] In response to the load change rate of the boiler being less than or equal to a first threshold, the water inlet flow of the boiler is adjusted with a second period; the first period is less than the second period.

[0129] In this embodiment, the drum water level is another key parameter in boiler operation. An excessively high water level can cause steam to carry water, degrading steam quality and potentially damaging turbine blades. A low water level can dry-burn the water-wall tubes, potentially leading to tube bursts. Therefore, during boiler control, the steam flow rate and water inlet flow rate must be balanced to ensure that parameters such as the drum water level remain within normal ranges.

[0130] When boilers need to frequently adjust load to meet grid or production demands, steam flow rates fluctuate constantly, and the drum water level fluctuates significantly. For example, during peak load periods, power plants must frequently increase or decrease boiler loads based on grid dispatch instructions. This requires reducing the inlet flow adjustment cycle to ensure timely adjustments and maintain a stable drum water level.

[0131] When the boiler is operating at a stable load, steam flow fluctuations are minimal, and the drum water level is relatively stable, the inlet flow regulation cycle can be appropriately increased. For example, during periods of low grid load, when the power plant boiler is operating at a low and stable load, a longer regulation cycle can be used.

[0132] Specifically, the feedwater flow rate can be adjusted by comparing the deviation between the measured value of the drum water level and the set value. If the deviation is greater than zero, that is, the water level is higher than the set value, the feedwater flow rate needs to be reduced; conversely, if it is less than zero, the feedwater flow rate needs to be increased. Therefore, the feedwater flow rate can be feedback controlled based on the drum water level signal. At the same time, according to the material balance relationship, when the steam flow rate increases, the feedwater flow rate needs to be increased accordingly. Therefore, the feedforward control of the feedwater flow rate can be performed based on the steam flow rate, adjusting the feedwater flow rate in advance to adapt to the changes in the steam flow rate.

[0133] For example, the water inlet flow rate can be calculated using the following first formula:

[0134] G=K1h+K2D+G f ; Among them, G represents the water inlet flow, h represents the deviation between the drum water level measurement value and the set value, D represents the total steam flow, G f Indicates the measured value of water inlet flow, K1 and K2 are both preset adjustment coefficients.

[0135] As can be seen from the above, this embodiment shortens the adjustment period when the load changes dramatically, enabling rapid response to load changes, preventing large water level fluctuations, and ensuring stable boiler operation. It also extends the adjustment period when the load changes gently, reducing unnecessary adjustments. Furthermore, this embodiment performs feedback-feedforward control of the boiler inlet flow rate based on the drum water level and steam flow rate, improving the accuracy and stability of drum water level control and ensuring safe and stable boiler operation.

[0136] Corresponding to the power plant boiler control method of the above embodiment, Figure 2 This is a structural block diagram of a power plant boiler control system provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The power plant boiler control system 20 includes: a first processing module 21, a second processing module 22, a first calculation module 23 and a first control module 24.

[0137] The first processing module 21 is configured to determine the first control model as the target control model in response to the load change rate of the boiler being greater than a first threshold;

[0138] The second processing module 22 is configured to determine the second control model as the target control model in response to the load change rate of the boiler being less than or equal to the first threshold; the accuracy of the first control model is less than the accuracy of the second control model;

[0139] The first calculation module 23 is used to input the boiler combustion parameters into the target control model to obtain the air-coal ratio;

[0140] The first control module 24 is used to control the combustion of the boiler based on the air-coal ratio.

[0141] In one embodiment of the present disclosure, the first control model and the second control model are both multilayer perceptron models, and the number of hidden layers of the first control model is smaller than the number of hidden layers of the second control model.

[0142] In one embodiment of the present disclosure, the first calculation module 23 is specifically configured to:

[0143] performing grayscale processing on the first flame image to obtain a second flame image;

[0144] extracting an edge contour of the flame area from the second flame image;

[0145] determining the flame intensity based on the grayscale value of the flame area;

[0146] The flame shape is determined based on the edge contour of the flame area.

[0147] In one embodiment of the present disclosure, the first calculation module 23 is further configured to:

[0148] Obtaining the first edge of the flame area based on the edge detection algorithm;

[0149] The first edge is sequentially subjected to dilation and erosion operations to obtain an edge contour of the flame region.

[0150] In one embodiment of the present disclosure, the first calculation module 23 is further configured to:

[0151] determining a shape of the structural element based on a noise distribution of the second flame image;

[0152] determining a size of the structural element based on a noise size of the second flame image;

[0153] Based on the structure element, the dilation operation and the erosion operation are sequentially performed on the first edge to obtain the edge contour of the flame area.

[0154] In one embodiment of the present disclosure, the first calculation module 23 is further configured to:

[0155] Calculating a first difference in grayscale value between each pixel and adjacent pixels in the second flame image;

[0156] In response to the proportion of first pixels in the second flame image being less than or equal to a second threshold, determining the shape of the structural element as a circle; the first pixel being a pixel for which the sum of the absolute values of the corresponding plurality of first differences is greater than a third threshold;

[0157] In response to the proportion of the first pixel points in the second flame image being greater than a second threshold, the shape of the structural element is determined to be a cross.

[0158] In one embodiment of the present disclosure, the first control module 24 is specifically configured to:

[0159] In response to the rate of change of the steam flow of the boiler being greater than a fourth threshold, the water inlet flow of the boiler is increased by a first step.

[0160] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided by an embodiment of the present invention. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules / units in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 24 are shown.

[0161] It should be understood that in the embodiments of the present disclosure, the processor 301 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0162] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0163] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0164] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the power plant boiler control method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0165] In another embodiment of the present disclosure, a computer-readable storage medium is provided, which stores a computer program, which includes program instructions. When the program instructions are executed by the processor, all or part of the process in the above-mentioned embodiment method is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0166] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0167] Those skilled in the art will 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 above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can 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 disclosure.

[0168] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0170] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the embodiments of the present disclosure.

[0171] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0172] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or replacements within the technical scope disclosed in this disclosure, and such modifications or replacements should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A power plant boiler control method, characterized in that The following steps are involved: S101: In response to a boiler load change rate being greater than a first threshold, determining a first control model as a target control model; S102: In response to the boiler load change rate being less than or equal to a first threshold, determining the second control model as the target control model, and the accuracy of the first control model is less than the accuracy of the second control model; S103, inputting the boiler combustion parameters into the target control model to obtain the air-coal ratio; S104. Control the combustion of the boiler based on the air-coal ratio.

2. A power plant boiler control method according to claim 1, characterized in that: The first control model and the second control model are both multi-layer perceptron models, and the number of hidden layers in the first control model is smaller than the number of hidden layers in the second control model.

3. A power plant boiler control method according to claim 1, characterized in that: In step S103, the combustion parameters include the flame intensity and flame shape of the burner, and the specific steps are as follows: performing grayscale processing on the first flame image to obtain a second flame image; extracting an edge contour of the flame area from the second flame image; determining the flame intensity based on the grayscale value of the flame area; The flame shape is determined based on the edge contour of the flame area.

4. A power plant boiler control method according to claim 3, characterized in that: The step of extracting the edge contour of the flame area from the second flame image includes: Obtaining the first edge of the flame area based on the edge detection algorithm; The first edge is sequentially subjected to dilation and erosion operations to obtain an edge contour of the flame region.

5. A power plant boiler control method according to claim 4, characterized in that: The step of sequentially performing an expansion operation and an erosion operation on the first edge to obtain an edge contour of the flame area includes: determining a shape of the structural element based on a noise distribution of the second flame image; determining a size of the structural element based on a noise size of the second flame image; Based on the structure element, the dilation operation and the erosion operation are sequentially performed on the first edge to obtain the edge contour of the flame area.

6. A power plant boiler control method according to claim 5, characterized in that: The determining the shape of the structural element based on the noise distribution of the second flame image comprises: Calculating a first difference in grayscale value between each pixel and adjacent pixels in the second flame image; In response to the proportion of first pixels in the second flame image being less than or equal to a second threshold, determining the shape of the structural element as a circle; the first pixel being a pixel for which the sum of the absolute values of the corresponding plurality of first differences is greater than a third threshold; In response to the proportion of the first pixel points in the second flame image being greater than a second threshold, the shape of the structural element is determined to be a cross.

7. The power plant boiler control method according to claim 1, characterized in that: It also includes the following steps: In response to a load change rate of the boiler being greater than a first threshold, adjusting the water inlet flow rate of the boiler with a first cycle; In response to a load change rate of the boiler being less than or equal to a first threshold, adjusting the water inlet flow rate of the boiler with a second period; The first period is smaller than the second period.

8. A power plant boiler control system, characterized by: The system comprises a first processing module (21), a second processing module (22), a first calculation module (23) and a first control module (24), wherein the first processing module (21) and the second processing module (22) respectively carry a first control model and a second control model, the first processing module (21) and the second processing module (22) are connected to the first calculation module (23), and the first calculation module (23) is connected to the first control module (24).

9. An electronic device, characterized in that: The invention comprises a memory (304), a processor (301) and a computer program, wherein the computer program is stored in the memory (304) and runs on the processor (301), and when the processor (301) executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images