Boiler combustion state evaluation method and system

Abstract

The invention discloses a boiler combustion state evaluation method and system, and the method comprises the steps: obtaining and preprocessing a flame distribution image in a boiler, obtaining a preprocessed image, carrying out the region division of the preprocessed image, and obtaining a plurality of flame regions; performing image analysis on flames in the flame area, determining a preset image feature value, and evaluating the combustion state of the flames based on the preset image feature value to obtain a flame combustion state evaluation value; position distribution and average temperature of the flame area in the boiler are determined, and a combustion distribution coefficient of the flame area is determined based on the position distribution and the average temperature; and determining a comprehensive combustion state evaluation value of the boiler based on the combustion distribution coefficient of the flame area and the flame combustion state evaluation value so as to evaluate the combustion state of the boiler. The boiler combustion state is evaluated based on flame image analysis, the combustion information of the whole hearth section can be obtained, the combustion state in the boiler can be accurately and comprehensively evaluated, and continuously improved technical support is provided for subsequent combustion management and optimization control of the boiler.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of boilers, in particular to a boiler combustion state evaluation method and system. BACKGROUND

[0002] In the energy industry field, as a core thermal equipment, the combustion state of a boiler is directly related to the power generation efficiency, operation cost, equipment safety and environmental protection emission.

[0003] Traditional boiler combustion state monitoring mainly relies on discrete point measurement methods, such as thermocouple thermometers, oxygen analyzers and flue gas monitoring equipment. These methods have obvious limitations: they can only provide measurement data at local positions and cannot fully reflect the complex combustion conditions in the furnace; the measurement results have a lag and it is difficult to discover combustion abnormalities in time; more importantly, the spatial distribution form of the flame cannot be intuitively grasped. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a boiler combustion state evaluation method and system, comprising:

[0005] obtaining a flame distribution image in the boiler and pre-processing the flame distribution image to obtain a pre-processed image;

[0006] analyzing the flame distribution in the pre-processed image and dividing the pre-processed image into regions based on the analysis result to obtain a plurality of flame regions;

[0007] performing image analysis on the flame in the flame region, determining a preset image feature value, and evaluating the combustion state of the flame based on the preset image feature value to obtain a flame combustion state evaluation value;

[0008] determining the position distribution and average temperature of the flame region in the boiler, and determining a combustion distribution coefficient of the flame region based on the position distribution and average temperature;

[0009] determining a comprehensive combustion state evaluation value of the boiler based on the combustion distribution coefficient of the flame region and the flame combustion state evaluation value to evaluate the combustion state of the boiler.

[0010] Further, the obtaining of the flame distribution image in the boiler and the pre-processing of the flame distribution image to obtain the pre-processed image comprises:

[0011] obtaining a flame distribution image in the boiler and pre-processing the flame distribution image to obtain a pre-processed image, the pre-processing including image denoising, image enhancement, image segmentation and image standardization processing.

[0012] Furthermore, the distribution of flames in the preprocessed image is analyzed, and based on the analysis results, the preprocessed image is divided into regions to obtain multiple flame regions, including:

[0013] The preprocessed image is converted to grayscale to obtain a grayscale image, and the grayscale value of all pixels in the grayscale image is determined.

[0014] A grayscale dataset is established based on the grayscale values ​​of pixels in a grayscale image, and k initial cluster centers are randomly selected from the grayscale dataset.

[0015] Calculate the Euclidean distance from the gray values ​​in the grayscale dataset to the initial cluster centers, and then assign each pixel to its corresponding cluster based on the Euclidean distance from the gray values ​​in the grayscale dataset to the initial cluster centers.

[0016] Calculate the average gray value within each cluster, and redetermine the cluster centers based on the average gray value within each cluster;

[0017] Repeat the above steps until the cluster centers no longer change or the number of iterations reaches the preset iteration threshold, to obtain k clusters;

[0018] The preprocessed image is divided into regions based on the position of pixels in each cluster, resulting in multiple flame regions.

[0019] Furthermore, the step of performing image analysis on the flame in the flame region to determine preset image feature values ​​includes:

[0020] Image features are extracted from the flame region, and the brightness, color, and shape features of the flame region are determined as preset image features from the extracted image features;

[0021] Numerical analysis and calculation are performed on the brightness, color, and shape characteristics of the flame region, and the average brightness value, RGB component mean, and flame area value of the flame region are determined as preset image feature values ​​from the calculation results.

[0022] Furthermore, the evaluation of the flame's combustion state based on preset image feature values ​​to obtain a flame combustion state evaluation value includes:

[0023] Determine the baseline values ​​of preset image features, and calculate the difference between each preset image feature value and the corresponding baseline value of the preset image feature.

[0024] The obtained differences are evaluated and values ​​are assigned to obtain the difference evaluation values ​​of each preset image feature. The preset image feature values ​​are then normalized to obtain the weights of each preset image feature.

[0025] The flame combustion state evaluation value is obtained by calculating the difference evaluation value and corresponding weight of each preset image feature.

[0026] Furthermore, the formula for calculating the flame combustion state assessment value of the flame region is as follows:

[0027] ,

[0028] Where P is the flame combustion state evaluation value of the flame region, αi is the weight of the i-th preset image feature, Ci is the difference evaluation value of the i-th preset image feature, and n is the number of preset image features.

[0029] Furthermore, determining the location distribution and average temperature of the flame zone within the boiler, and determining the combustion distribution coefficient of the flame zone based on the location distribution and average temperature, includes:

[0030] A preset position coefficient-position distribution range correspondence is set in advance. For each position distribution range, a corresponding preset position coefficient is associated with it.

[0031] The location distribution of each flame region is obtained, and based on the mapping relationship between the location distribution range to which the location distribution belongs and the preset location coefficient-location distribution range correspondence, the preset location coefficient corresponding to the location distribution range is selected as the location coefficient of each flame region.

[0032] Determine the average temperature of each flame region, and determine the highest average temperature based on the average temperature of each flame region;

[0033] The combustion distribution coefficient of the flame zone is obtained by calculation based on the location coefficient, average temperature, and maximum average temperature.

[0034] Furthermore, the formula for calculating the combustion distribution coefficient of the flame region is as follows:

[0035] ,

[0036] Where S is the combustion distribution coefficient of the flame area, β is the first preset weight, G is the position coefficient value, γ is the second preset weight, T is the average temperature, and Tmax is the highest average temperature.

[0037] Furthermore, the determination of the boiler's comprehensive combustion state assessment value based on the combustion distribution coefficient of the flame region and the flame combustion state assessment value to evaluate the boiler's combustion state includes:

[0038] The combustion distribution coefficient and the flame combustion state evaluation value of each flame region are multiplied to obtain the sub-combustion state evaluation value of each flame region.

[0039] The sub-combustion state evaluation values ​​of each flame zone are added together to obtain the comprehensive combustion state evaluation value of the boiler, and the combustion state of the boiler is evaluated based on the comprehensive combustion state evaluation value.

[0040] The present invention also provides a boiler combustion status assessment system, comprising:

[0041] The preprocessing module is used to acquire flame distribution images inside the boiler and preprocess the flame distribution images to obtain preprocessed images.

[0042] The segmentation module is used to analyze the flame distribution in the preprocessed image and divide the preprocessed image into regions based on the analysis results, resulting in multiple flame regions.

[0043] The evaluation module is used to perform image analysis on the flame in the flame area, determine the preset image feature values, and evaluate the combustion state of the flame based on the preset image feature values ​​to obtain the flame combustion state evaluation value.

[0044] The determination module is used to determine the location distribution and average temperature of the flame zone within the boiler, and to determine the combustion distribution coefficient of the flame zone based on the location distribution and average temperature.

[0045] The calculation module is used to determine the comprehensive combustion state assessment value of the boiler based on the combustion distribution coefficient of the flame area and the flame combustion state assessment value, so as to evaluate the combustion state of the boiler.

[0046] Compared with the prior art, the boiler combustion state assessment method and system of this invention have the following advantages:

[0047] This invention captures real-time images of the flame distribution inside a boiler using a high-temperature industrial camera, breaking through the limitations of traditional point-based measurements and achieving a technological leap from "local perception" to "full-field visualization." Furthermore, the preprocessing of the images effectively overcomes the interference of the high-temperature and high-dust environment inside the boiler on image quality, ensuring the clear extraction of flame features and laying a solid foundation for subsequent accurate analysis.

[0048] This invention is based on intelligent region division technology of flame distribution characteristics, which can accurately identify the flame region corresponding to different burners in the boiler, realize the transformation from coarse overall assessment to fine local diagnosis, and accurately locate the specific location and cause of combustion abnormality.

[0049] This invention innovatively combines flame combustion state assessment values ​​with combustion distribution coefficients to establish a comprehensive evaluation model that takes into account combustion efficiency, stability, and safety. The integration of the two ensures the comprehensiveness and accuracy of the evaluation results, providing precise guidance for operational optimization. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the process structure of the boiler combustion state assessment method in an embodiment of the present invention;

[0051] Figure 2 This is a schematic diagram of the composition of the boiler combustion status assessment system in an embodiment of the present invention. Detailed Implementation

[0052] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0053] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0054] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0055] like Figure 1 As shown in the embodiments of this application, a boiler combustion state assessment method is provided, including: S100: acquiring a flame distribution image inside the boiler and preprocessing the flame distribution image to obtain a preprocessed image; S200: analyzing the flame distribution in the preprocessed image and dividing the preprocessed image into regions based on the analysis results to obtain multiple flame regions; S300: performing image analysis on the flames in the flame regions to determine preset image feature values, and assessing the combustion state of the flames based on the preset image feature values ​​to obtain a flame combustion state assessment value; S400: determining the location distribution and average temperature of the flame regions inside the boiler, and determining the combustion distribution coefficient of the flame regions based on the location distribution and average temperature; S500: determining the comprehensive combustion state assessment value of the boiler based on the combustion distribution coefficient of the flame regions and the flame combustion state assessment value, so as to assess the combustion state of the boiler.

[0056] Furthermore, this invention captures real-time images of the flame distribution inside the boiler using a high-temperature industrial camera, overcoming the limitations of traditional point-based measurements and achieving a technological leap from "local perception" to "full-field visualization." Image preprocessing effectively overcomes the interference of the high-temperature, high-dust environment inside the boiler on image quality, ensuring clear extraction of flame features and laying a solid foundation for subsequent precise analysis. Based on intelligent region segmentation technology for flame distribution characteristics, this invention can accurately identify the flame regions corresponding to different burners within the boiler, achieving a shift from coarse overall assessment to refined local diagnosis, and accurately locating the specific location and cause of combustion anomalies. This invention innovatively combines flame combustion state assessment values ​​with combustion distribution coefficients to establish a comprehensive evaluation model that considers combustion efficiency, stability, and safety. The fusion of these two factors ensures the comprehensiveness and accuracy of the assessment results, providing precise guidance for operational optimization.

[0057] In an embodiment of this application, a method for evaluating the combustion state of a boiler is provided. The step of acquiring a flame distribution image inside the boiler and preprocessing the flame distribution image to obtain a preprocessed image includes: acquiring a flame distribution image inside the boiler and preprocessing the flame distribution image to obtain a preprocessed image. The preprocessing includes image denoising, image enhancement, image segmentation, and image normalization.

[0058] Specifically, high-temperature industrial cameras installed at the boiler observation port acquire real-time images of the flame distribution inside the furnace, and systematically preprocess these images to lay a solid foundation for subsequent combustion state analysis. The preprocessing process begins with image denoising, employing adaptive median filtering combined with wavelet thresholding to effectively eliminate image noise caused by high-temperature radiation, dust interference, and electronic noise, while preserving flame edge details to the maximum extent. Next, image enhancement is performed, significantly improving image contrast and clarity through contrast-limited adaptive histogram equalization and homomorphic filtering, enhancing the distinction between the flame area and the background, and making the internal structural features of the flame more apparent. Then, image segmentation is performed, using an improved Otsu thresholding algorithm combined with region growing technology to accurately separate the flame area from the furnace background, generating an accurate binary mask image. Finally, image standardization is performed, including size normalization, grayscale normalization, and color correction, eliminating image inconsistencies caused by variations in camera parameters, shooting angles, and lighting conditions, ensuring the reliability and comparability of subsequent feature extraction. This step effectively overcomes the technical challenges posed by the harsh imaging environment inside the boiler, transforming the original blurry and noisy flame images into clear, regular, and standard analysis samples. This provides reliable data support for subsequent flame feature extraction, region division, and intelligent combustion state assessment, significantly improving the accuracy and robustness of the entire combustion state analysis system.

[0059] In an embodiment of this application, a boiler combustion state assessment method is provided. The method involves analyzing the flame distribution in a preprocessed image and dividing the preprocessed image into regions based on the analysis results to obtain multiple flame regions. The method includes: converting the preprocessed image to grayscale to obtain a grayscale image and determining the grayscale value of all pixels within the grayscale image; establishing a grayscale dataset based on the grayscale values ​​of the pixels in the grayscale image and randomly selecting k initial cluster centers from the grayscale dataset; calculating the Euclidean distance from the grayscale values ​​in the grayscale dataset to the initial cluster centers and dividing each pixel into its corresponding cluster based on the Euclidean distance; calculating the average grayscale value within each cluster and re-determining the cluster centers based on the average grayscale value within each cluster; repeating the above steps iteratively until the cluster centers no longer change or the number of iterations reaches a preset iteration threshold, resulting in k clusters; and dividing the preprocessed image into regions based on the positions of the pixels in each cluster to obtain multiple flame regions.

[0060] Specifically, the color flame image is converted into a grayscale image to obtain the grayscale value information of each pixel, forming a complete grayscale dataset. K cluster centers are randomly initialized, and the Euclidean distance between the grayscale value of each pixel and the cluster center is calculated iteratively to dynamically assign pixels to the nearest cluster. During each iteration, the system recalculates the average grayscale value of pixels within each cluster and updates the cluster center position accordingly. Through continuous optimization, the cluster centers gradually converge to a stable state. When the cluster centers no longer change or the preset number of iterations is reached, the algorithm terminates, ultimately dividing the entire flame image into k clustered regions with similar grayscale characteristics. This step achieves adaptive identification of flame regions, automatically dividing areas of different brightness based on the image's own characteristics without the need for pre-setting thresholds. It accurately identifies key areas such as the high-temperature core area, the main combustion zone, and the peripheral low-temperature zone, achieving high accuracy. This step also has good anti-interference capabilities, effectively overcoming the influence of factors such as uneven lighting and dust interference within the boiler, ensuring precise delineation of area boundaries. The data-driven segmentation method lays a solid foundation for subsequent quantitative assessment of combustion status, making region-based feature extraction and status analysis more scientific and reliable. It significantly improves the automation level and assessment accuracy of boiler combustion status monitoring, providing precise regional guidance for combustion optimization control.

[0061] In an embodiment of this application, a boiler combustion state assessment method is provided. The step of performing image analysis on the flame in the flame region to determine preset image feature values ​​includes: extracting image features from the flame region and determining the brightness, color, and shape features of the flame region as preset image features from the extracted image features; performing numerical analysis and calculation on the brightness, color, and shape features of the flame region and determining the average brightness value, the average RGB component value, and the flame area value of the flame region as preset image feature values ​​from the calculation results.

[0062] Specifically, by extracting multi-dimensional image features from each divided flame region, three key visual features—brightness, color, and shape—were selected as preset analysis indicators. For brightness, the average brightness value reflecting the flame radiation intensity was obtained by calculating the average grayscale value of all pixels in the region. For color, the average pixel values ​​of the red, green, and blue channels in the RGB color space were extracted to construct the average RGB component values ​​characterizing the flame color temperature distribution and combustion product characteristics. For shape, the flame area value reflecting the flame diffusion range and actual size was calculated by counting the total number of pixels in the region and combining it with spatial calibration parameters. This step overcomes the limitations of single-feature characterization by using a multi-feature fusion analysis method. The average brightness value accurately reflects combustion intensity and temperature level, the average RGB component can effectively identify changes in the composition of combustion products and abnormal combustion conditions, and the flame area value directly reflects the mixing status of fuel and air and the degree of combustion completeness. Feature quantification based on numerical calculation transforms the assessment of combustion status from subjective experience judgment to objective data analysis, significantly improving the accuracy and repeatability of the assessment results. This step lays a solid foundation for the subsequent establishment of a combustion status assessment model. Through comprehensive analysis of feature values, the system can achieve a comprehensive assessment of combustion efficiency, stability, and environmental friendliness, providing a scientific basis for the refined control and intelligent operation of boilers, and significantly improving the controllability and operational economy of the combustion process.

[0063] In an embodiment of this application, a boiler combustion state assessment method is provided. The method for assessing the combustion state of a flame based on preset image feature values ​​to obtain a flame combustion state assessment value includes: determining a preset baseline value for a preset image feature, and calculating the difference between each preset image feature value and the corresponding baseline value; evaluating the obtained differences to obtain a difference assessment value for each preset image feature, and normalizing each preset image feature value to obtain a weight for each preset image feature; and calculating the flame combustion state assessment value based on the difference assessment value and the corresponding weight of each preset image feature.

[0064] Specifically, based on extensive historical data of the boiler under optimal operating conditions, baseline values ​​for each preset image feature are determined. These baseline values ​​represent the feature levels under ideal combustion conditions. The absolute differences between each feature value in the current flame region and its corresponding baseline value are calculated, and these differences are transformed into standardized difference evaluation values ​​through a preset evaluation function. Each feature value is normalized to determine its weight allocation. A weighted sum is calculated based on the difference evaluation values ​​of each preset image feature and their corresponding weights to obtain the flame combustion state evaluation value. This step, based on the difference analysis of baseline values, provides the evaluation results with clear reference standards and physical meaning, intuitively reflecting the degree of deviation between the current combustion state and ideal operating conditions. The adaptive weight allocation mechanism ensures the dominant role of key features in the evaluation, avoiding the subjectivity and limitations of manually setting weights, and enabling the evaluation model to have self-learning and self-optimization capabilities. By fusing multi-dimensional feature information into a single evaluation value through mathematical methods, the complexity of state judgment is greatly simplified, allowing operators to quickly grasp the combustion status directly based on the evaluation value, improving decision-making efficiency.

[0065] In an embodiment of this application, a boiler combustion state assessment method is provided, wherein the calculation formula for the flame combustion state assessment value of the flame zone is:

[0066] ,

[0067] Where P is the flame combustion state evaluation value of the flame region, αi is the weight of the i-th preset image feature, Ci is the difference evaluation value of the i-th preset image feature, and n is the number of preset image features.

[0068] In an embodiment of this application, a method for evaluating boiler combustion status is provided. The method involves determining the location distribution and average temperature of flame regions within the boiler, and determining the combustion distribution coefficient of the flame regions based on the location distribution and average temperature. This includes: pre-setting a preset location coefficient-location distribution range correspondence, where each location distribution range is associated with a corresponding preset location coefficient; acquiring the location distribution of each flame region, and based on the mapping relationship between the location distribution range and the preset location coefficient-location distribution range correspondence, selecting the preset location coefficient corresponding to the location distribution range as the location coefficient for each flame region; determining the average temperature of each flame region, and determining the highest average temperature based on the average temperature of each flame region; and calculating the combustion distribution coefficient of the flame regions based on the location coefficient, average temperature, and highest average temperature.

[0069] Specifically, by pre-setting the correspondence between position coefficients and position distribution ranges, the boiler furnace is divided into different position ranges such as the core combustion zone, transition zone, and edge zone, and each range is assigned a corresponding position coefficient, with the core combustion zone having the highest coefficient and the edge zone having the lowest coefficient. After obtaining the actual position distribution of each flame region, the system automatically matches the corresponding position coefficient according to its position range, while accurately calculating the real-time average temperature of each region and determining the highest average temperature in all regions as a reference benchmark. Based on these parameters, a weighted calculation model is used to combine the position coefficient, the ratio of the region's average temperature to the highest average temperature to generate the combustion distribution coefficient for each flame region. This step introduces a location coefficient, ensuring the evaluation results fully consider the impact of spatial location on combustion quality. This avoids evaluation biases that may arise from relying solely on temperature indicators, enhancing the comprehensiveness and scientific rigor of the evaluation. By standardizing the comparison between regional temperatures and the highest temperature, the limitations of absolute temperature values ​​being affected by load changes are eliminated, making the evaluation results under different operating conditions comparable. The combustion distribution coefficient calculation model can sensitively reflect the unevenness of flame distribution. When abnormalities such as flame deviation, localized high temperatures, or combustion center shift occur, the distribution coefficient of the relevant area will significantly decrease, providing clear guidance for operational adjustments. This step provides crucial spatial distribution dimension information for subsequent comprehensive combustion status evaluation, effectively complementing the combustion status evaluation values ​​and jointly constructing a more complete boiler combustion quality evaluation system. This lays a solid foundation for achieving refined management and intelligent control of the combustion process, effectively improving the safety, economy, and environmental friendliness of boiler operation.

[0070] In an embodiment of this application, a boiler combustion state assessment method is provided, wherein the calculation formula for the combustion distribution coefficient of the flame region is:

[0071] ,

[0072] Where S is the combustion distribution coefficient of the flame area, β is the first preset weight, G is the position coefficient value, γ is the second preset weight, T is the average temperature, and Tmax is the highest average temperature.

[0073] In an embodiment of this application, a method for evaluating boiler combustion status is provided. The method for determining a comprehensive combustion status evaluation value of the boiler based on the combustion distribution coefficient of each flame region and the flame combustion status evaluation value, in order to evaluate the combustion status of the boiler, includes: multiplying the combustion distribution coefficient and the flame combustion status evaluation value of each flame region to obtain a sub-combustion status evaluation value for each flame region; adding the sub-combustion status evaluation values ​​of each flame region to obtain a comprehensive combustion status evaluation value for the boiler; and evaluating the combustion status of the boiler based on the comprehensive combustion status evaluation value.

[0074] Specifically, the combustion distribution coefficient of each flame region is multiplied by the flame combustion state assessment value to obtain the sub-combustion state assessment value of each region. This multiplication operation ensures that the coupling effect of the two dimensions of spatial distribution rationality and combustion quality is fully reflected. Even if the combustion state of a certain region is good, its sub-assessment value will be reduced accordingly if the location distribution is unreasonable, and vice versa. The sub-combustion state assessment values ​​of all flame regions are weighted or simply added to obtain the comprehensive combustion state assessment value of the boiler. This value comprehensively reflects the overall quality level of the combustion process inside the boiler. This step avoids the limitations of relying on a single indicator to dominate the evaluation results through a multiplicative fusion mechanism, ensuring a balanced consideration of the two key dimensions of spatial distribution and combustion quality, making the evaluation results more comprehensive and objective. By accumulating the regional sub-evaluation values, it considers both the combustion status of each local area and reflects the synergistic effect of overall combustion, accurately identifying the impact of anomalies in specific areas on the entire system. The output of the comprehensive evaluation value greatly simplifies the judgment of operators, and the single quantitative indicator facilitates quick understanding of the overall combustion status of the boiler, supporting real-time decision-making and timely intervention, and improving response speed. This step provides a unified standard for trend analysis, performance comparison, and optimization effect verification of boiler combustion status, making the combustion status of different boilers and at different times comparable, laying a solid foundation for continuous optimization and intelligent management of the combustion system, and effectively promoting the improvement of boiler operating efficiency and the reduction of energy consumption.

[0075] like Figure 2 As shown in the embodiments of this application, a boiler combustion state assessment system is provided, comprising: a preprocessing module for acquiring flame distribution images within the boiler and preprocessing the flame distribution images to obtain a preprocessed image; a segmentation module for analyzing the flame distribution in the preprocessed image and segmenting the preprocessed image into regions based on the analysis results to obtain multiple flame regions; an assessment module for performing image analysis on the flames in the flame regions, determining preset image feature values, and assessing the combustion state of the flames based on the preset image feature values ​​to obtain a flame combustion state assessment value; a determination module for determining the location distribution and average temperature of the flame regions within the boiler, and determining the combustion distribution coefficient of the flame regions based on the location distribution and average temperature; and a calculation module for determining the comprehensive combustion state assessment value of the boiler based on the combustion distribution coefficient of the flame regions and the flame combustion state assessment value, thereby assessing the combustion state of the boiler.

[0076] In summary, this invention provides a boiler combustion state assessment method and system, comprising: acquiring and preprocessing flame distribution images within the boiler to obtain preprocessed images, and dividing them into regions to obtain multiple flame regions; performing image analysis on the flames within the flame regions to determine preset image feature values, and assessing the combustion state of the flames based on these features to obtain flame combustion state assessment values; determining the location distribution and average temperature of the flame regions within the boiler, and determining the combustion distribution coefficient of the flame regions based on these values; and determining the comprehensive combustion state assessment value of the boiler based on the combustion distribution coefficient of the flame regions and the flame combustion state assessment values, thereby assessing the boiler's combustion state. This invention assesses boiler combustion state based on flame image analysis, enabling the acquisition of combustion information across the entire furnace cross-section. It can accurately and comprehensively assess the combustion state within the boiler, providing continuous technical support for subsequent combustion management and optimized control of the boiler.

[0077] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0078] The above description is merely one embodiment of the present invention, and should not be construed as limiting the scope of the invention. Any structural changes made based on the present invention, as long as they do not depart from the essence of the invention, should be considered as falling within the protection scope of the present invention and subject to its restrictions. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the platform described above can be referred to the corresponding processes in the foregoing platform embodiments, and will not be repeated here.

[0079] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, platform, article, or device / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to those processes, platforms, articles, or devices / platforms.

[0080] The technical solutions of the present invention have been described in conjunction with the accompanying drawings and further embodiments. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions resulting from such changes or substitutions will all fall within the scope of protection of the present invention.

[0081] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A method for assessing boiler combustion status, characterized in that, include: Acquire images of the flame distribution inside the boiler and preprocess the flame distribution images to obtain preprocessed images; The distribution of flames in the preprocessed image is analyzed, and the preprocessed image is divided into regions based on the analysis results to obtain multiple flame regions; Image analysis is performed on the flame in the flame area to determine the preset image feature values, and the combustion state of the flame is evaluated based on the preset image feature values ​​to obtain the flame combustion state evaluation value. Determine the location distribution and average temperature of the flame zone within the boiler, and determine the combustion distribution coefficient of the flame zone based on the location distribution and average temperature; The comprehensive combustion status assessment value of the boiler is determined based on the combustion distribution coefficient of the flame zone and the flame combustion status assessment value, in order to evaluate the combustion status of the boiler.

2. A boiler combustion state assessment method according to claim 1, characterized in that, The process of acquiring a flame distribution image inside the boiler and preprocessing the flame distribution image to obtain a preprocessed image includes: The flame distribution image inside the boiler is acquired and preprocessed to obtain a preprocessed image. The preprocessing includes image denoising, image enhancement, image segmentation, and image normalization.

3. A boiler combustion state assessment method according to claim 2, characterized in that, The process involves analyzing the flame distribution in the preprocessed image and dividing the image into regions based on the analysis results, resulting in multiple flame regions, including: The preprocessed image is converted to grayscale to obtain a grayscale image, and the grayscale value of all pixels in the grayscale image is determined. A grayscale dataset is established based on the grayscale values ​​of pixels in a grayscale image, and k initial cluster centers are randomly selected from the grayscale dataset. Calculate the Euclidean distance from the gray values ​​in the grayscale dataset to the initial cluster centers, and then assign each pixel to its corresponding cluster based on the Euclidean distance from the gray values ​​in the grayscale dataset to the initial cluster centers. Calculate the average gray value within each cluster, and redetermine the cluster centers based on the average gray value within each cluster; Repeat the above steps until the cluster centers no longer change or the number of iterations reaches the preset iteration threshold, to obtain k clusters; The preprocessed image is divided into regions based on the position of pixels in each cluster, resulting in multiple flame regions.

4. A boiler combustion state assessment method according to claim 3, characterized in that, The step of performing image analysis on the flame in the flame region to determine preset image feature values ​​includes: Image features are extracted from the flame region, and the brightness, color, and shape features of the flame region are determined as preset image features from the extracted image features; Numerical analysis and calculation are performed on the brightness, color, and shape characteristics of the flame region, and the average brightness value, RGB component mean, and flame area value of the flame region are determined as preset image feature values ​​from the calculation results.

5. A boiler combustion state assessment method according to claim 4, characterized in that, The evaluation of the flame's combustion state based on preset image feature values ​​to obtain a flame combustion state evaluation value includes: Determine the baseline values ​​of preset image features, and calculate the difference between each preset image feature value and the corresponding baseline value of the preset image feature; The obtained differences are evaluated and values ​​are assigned to obtain the difference evaluation values ​​of each preset image feature. The preset image feature values ​​are then normalized to obtain the weights of each preset image feature. The flame combustion state evaluation value is obtained by calculating the difference evaluation value and corresponding weight of each preset image feature.

6. A boiler combustion state assessment method according to claim 5, characterized in that, The formula for calculating the flame combustion state assessment value of the flame zone is as follows: ， Where P is the flame combustion state evaluation value of the flame region, αi is the weight of the i-th preset image feature, Ci is the difference evaluation value of the i-th preset image feature, and n is the number of preset image features.

7. A boiler combustion state assessment method according to claim 5, characterized in that, The determination of the location distribution and average temperature of the flame zone within the boiler, and the determination of the combustion distribution coefficient of the flame zone based on the location distribution and average temperature, includes: A preset position coefficient-position distribution range correspondence is set in advance. For each position distribution range, a corresponding preset position coefficient is associated with it. The location distribution of each flame region is obtained, and based on the mapping relationship between the location distribution range to which the location distribution belongs and the preset location coefficient-location distribution range correspondence, the preset location coefficient corresponding to the location distribution range is selected as the location coefficient of each flame region. Determine the average temperature of each flame region, and determine the highest average temperature based on the average temperature of each flame region; The combustion distribution coefficient of the flame zone is obtained by calculation based on the location coefficient, average temperature, and maximum average temperature.

8. A boiler combustion state assessment method according to claim 7, characterized in that, The formula for calculating the combustion distribution coefficient of the flame region is: ， Where S is the combustion distribution coefficient of the flame area, β is the first preset weight, G is the position coefficient value, γ is the second preset weight, T is the average temperature, and Tmax is the highest average temperature.

9. A boiler combustion state assessment method according to claim 7, characterized in that, The comprehensive combustion state assessment value of the boiler is determined based on the combustion distribution coefficient of the flame region and the flame combustion state assessment value to evaluate the combustion state of the boiler, including: The combustion distribution coefficient and the flame combustion state evaluation value of each flame region are multiplied to obtain the sub-combustion state evaluation value of each flame region. The sub-combustion state evaluation values ​​of each flame zone are added together to obtain the comprehensive combustion state evaluation value of the boiler, and the combustion state of the boiler is evaluated based on the comprehensive combustion state evaluation value.

10. A boiler combustion status assessment system, characterized in that, include: The preprocessing module is used to acquire flame distribution images inside the boiler and preprocess the flame distribution images to obtain preprocessed images. The segmentation module is used to analyze the flame distribution in the preprocessed image and divide the preprocessed image into regions based on the analysis results, resulting in multiple flame regions. The evaluation module is used to perform image analysis on the flame in the flame area, determine the preset image feature values, and evaluate the combustion state of the flame based on the preset image feature values ​​to obtain the flame combustion state evaluation value. The determination module is used to determine the location distribution and average temperature of the flame zone within the boiler, and to determine the combustion distribution coefficient of the flame zone based on the location distribution and average temperature. The calculation module is used to determine the comprehensive combustion state assessment value of the boiler based on the combustion distribution coefficient of the flame area and the flame combustion state assessment value, so as to evaluate the combustion state of the boiler.

Images