Intelligent combustion optimization control system and method for boiler

Abstract

The invention relates to the technical field of boiler combustion control, and discloses a boiler intelligent combustion optimization control system and method, and the system comprises a judgment module which is used for obtaining boiler combustion thermal imaging data, determining a combustion stability coefficient of a current boiler according to the boiler combustion thermal imaging data, and outputting the combustion stability coefficient; judging whether combustion optimization is needed or not according to the combustion stability coefficient of the current boiler; the strategy module is used for obtaining current boiler operation data and operation load if combustion optimization is needed, and determining a current combustion optimization strategy according to the current boiler operation data and operation load; and the optimization module is used for determining a standard stability coefficient according to the current combustion optimization strategy and determining a final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler. The combustion state of the boiler in the operation process can be accurately monitored, and the combustion optimization strategy is formulated in time according to the combustion state, so that the boiler can keep stable combustion.

Description

Technical Field

[0001] The present application relates to the technical field of boiler combustion control, and more specifically, to a boiler intelligent combustion optimization control system and method. Background Art

[0002] At the current stage in my country, thermal power generation still occupies an important position in the development of electricity. Thermal power plants mainly generate electricity through boiler combustion. In the process of improving the conversion of fuel into electricity, the emission of pollutants and greenhouse gases is inevitable. With the introduction of a series of control standards and policies adopted by the state for environmental pollution, thermal power plants have actively and steadily promoted carbon peak and carbon neutrality by optimizing boiler combustion efficiency. Based on my country's energy resource endowment, they insist on building first and then breaking, and implement carbon peak action in a planned and step-by-step manner, deepen the energy revolution, strengthen the clean and efficient use of coal, and accelerate the planning and construction of a new energy system.

[0003] In the prior art, when the unit is in the process of flexible peak load regulation, the unit will often be in a low-load operation state. Since the flame of the combustion system of the coal-fired boiler is difficult to stabilize, the fuel cannot be fully utilized and the combustion efficiency of the unit is reduced. Summary of the invention

[0004] The present invention provides a boiler intelligent combustion optimization control system and method, which is used to solve the problem of flame stability in the boiler combustion system in the prior art, including:

[0005] A judgment module is used to obtain boiler combustion thermal imaging data, determine the combustion stability coefficient of the current boiler according to the boiler combustion thermal imaging data, and judge whether combustion optimization is needed according to the combustion stability coefficient of the current boiler;

[0006] The strategy module is used to obtain the current boiler operation data and operation load if combustion optimization is required, and determine the current combustion optimization strategy based on the current boiler operation data and operation load;

[0007] The optimization module is used to determine the standard stability coefficient according to the current combustion optimization strategy, and determine the final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler.

[0008] Furthermore, the judgment module determines the combustion stability coefficient of the current boiler according to the boiler combustion thermal imaging data, including:

[0009] Segment the boiler combustion thermal imaging data to obtain a number of combustion image blocks, and obtain the pixel value of each pixel in the combustion image block;

[0010] Determine the average pixel value of the burning image block according to the pixel value of each pixel point, calculate the difference between the average pixel value of the burning image block and the average pixel value of the remaining burning image blocks within the 8-neighborhood range, and establish a burning direction image according to the difference between the average pixel value of the burning image block and the average pixel value of the remaining burning image blocks within the 8-neighborhood range;

[0011] Calculate the degree of each burning image block in the burning direction image, obtain the average value of the pixel value difference between each burning image block and the adjacent burning image block in the burning direction image, multiply the average value of the pixel value difference by the corresponding degree, and obtain the stability coefficient of the burning image block;

[0012] The average value of the stability coefficients of all combustion image blocks in the combustion direction image is calculated to obtain the combustion stability coefficient of the boiler.

[0013] Furthermore, the burning direction image is established according to the difference between the burning image block and the average pixel value of the remaining burning image blocks within the 8-neighborhood range, including:

[0014] Screen out two burning image blocks whose average pixel value difference is greater than a first preset threshold, connect the two burning image blocks whose average pixel values ​​are greater than the first preset threshold, and obtain a burning direction image;

[0015] The adjacent burning image blocks that are not connected to the other burning image blocks are merged, and the merged burning image blocks are spliced ​​to obtain a burning direction image.

[0016] Furthermore, the judgment module judges whether combustion optimization is required according to the combustion stability coefficient of the current boiler, including:

[0017] Obtaining a preset combustion allowable coefficient, and calculating a difference between the preset combustion allowable coefficient and a combustion stability coefficient;

[0018] Determine whether the difference between the preset combustion permissible coefficient and the combustion stability coefficient is greater than a second preset threshold value, and if the difference between the preset combustion permissible coefficient and the combustion stability coefficient is greater than the second preset threshold value, determine that the boiler needs to be optimized for combustion;

[0019] If the difference between the preset combustion permissible coefficient and the combustion stability coefficient is less than or equal to the second preset threshold, it is determined that the boiler does not need to be optimized for combustion.

[0020] Furthermore, the strategy module determines the current combustion optimization strategy according to the current boiler operation data and operation load, including:

[0021] Obtain a boiler historical operation database, and determine the boiler historical operation parameters and operation load according to the boiler historical operation database;

[0022] A sample data set is established based on the historical operating parameters and operating load of the boiler, and k initial clustering centers of the sample data set are randomly selected;

[0023] Calculate the Euclidean distance from the sample value in the sample data set to the initial cluster center, and divide each sample data into corresponding partitions according to the Euclidean distance from the sample value in the sample data set to the initial cluster center;

[0024] Calculate the average value of the sample data in each partition, and re-determine the cluster center based on the average value of the sample data in each partition;

[0025] Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset iteration threshold, and obtain k final cluster centers;

[0026] The standard operation data and operation load of each cluster partition in the historical operation database are determined according to the final cluster center, a combustion optimization strategy model is established according to the standard operation data and operation load of each cluster partition, and the current combustion optimization strategy is determined according to the combustion optimization strategy model.

[0027] Furthermore, the combustion optimization strategy model is established according to the standard operation data and operation load of each cluster partition, and the current combustion optimization strategy is determined according to the combustion optimization strategy model, including:

[0028] Determine the combustion optimization strategy corresponding to the standard operation data and the operation load according to the boiler historical operation database, and establish a training sample set according to the standard operation data and the operation load and the corresponding combustion optimization strategy;

[0029] An initial combustion optimization strategy model is established, and the initial combustion optimization strategy model is trained according to a training sample set to obtain a trained combustion optimization strategy model;

[0030] The current boiler operation data and operation load are input into the trained combustion optimization strategy model to obtain the current combustion optimization strategy.

[0031] Furthermore, the optimization module determines the standard stability coefficient according to the current combustion optimization strategy, including:

[0032] Obtaining standard operation data of each cluster partition, determining the combustion thermal imaging data corresponding to the standard operation data of each cluster partition according to the boiler historical operation database, and calculating the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data;

[0033] The optimal stability coefficient is determined according to the current combustion optimization strategy, and the optimal stability coefficient is corrected according to the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data to obtain the standard stability coefficient.

[0034] Furthermore, the optimal stability coefficient is corrected according to the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data to obtain the standard stability coefficient, including:

[0035] The optimal stability coefficient is corrected according to the stability coefficient correction formula, and the stability coefficient correction formula is specifically:

[0036]

[0037] Among them, S α is the standard stability factor, S o is the optimal stability coefficient, M o is the preset standard matching degree, M α is the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data, and exp is the natural exponential function.

[0038] Furthermore, the optimization module determines a final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler, including:

[0039] The difference between the standard stability coefficient and the current combustion stability coefficient is calculated, the optimization adjustment speed is determined according to the difference between the standard stability coefficient and the current combustion stability coefficient, and the final combustion optimization strategy is determined according to the optimization adjustment speed.

[0040] In order to achieve the above object, the present invention also provides a boiler intelligent combustion optimization control method, comprising:

[0041] Obtain boiler combustion thermal imaging data, determine the combustion stability coefficient of the current boiler based on the boiler combustion thermal imaging data, and determine whether combustion optimization is needed based on the combustion stability coefficient of the current boiler;

[0042] If combustion optimization is required, the current boiler operation data and operation load are obtained, and the current combustion optimization strategy is determined based on the current boiler operation data and operation load;

[0043] The standard stability coefficient is determined according to the current combustion optimization strategy, and the final combustion optimization strategy is determined according to the standard stability coefficient and the combustion stability coefficient of the current boiler.

[0044] The beneficial effects of the present invention are:

[0045] By applying the above technical scheme, the present invention obtains an accurate combustion stability coefficient by analyzing the boiler combustion thermal imaging data, and dynamically adjusts the boiler's combustion optimization strategy through the combustion stability coefficient, so that the boiler can maintain stable combustion and improve the boiler's thermal efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 A result schematic diagram of a boiler intelligent combustion optimization control system proposed in an embodiment of the present invention is shown;

[0048] Figure 2 The figure shows an overall flow chart of a boiler intelligent combustion optimization control method proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The present application embodiment provides a boiler intelligent combustion optimization control system, such as Figure 1 As shown, including:

[0051] The judgment module is used to obtain boiler combustion thermal imaging data, determine the combustion stability coefficient of the current boiler based on the boiler combustion thermal imaging data, and judge whether combustion optimization is needed based on the combustion stability coefficient of the current boiler; the strategy module is used to obtain the current boiler operation data and operation load if combustion optimization is needed, and determine the current combustion optimization strategy based on the current boiler operation data and operation load; the optimization module is used to determine the standard stability coefficient based on the current combustion optimization strategy, and determine the final combustion optimization strategy based on the standard stability coefficient and the combustion stability coefficient of the current boiler.

[0052] In this embodiment, a fixed infrared thermal imaging camera is used to collect boiler combustion thermal imaging data, and whether combustion optimization is needed is determined based on the real-time combustion stability coefficient. If combustion optimization is needed, the current boiler operating data and operating load are collected to establish a combustion optimization strategy. At the same time, the combustion optimization strategy is adjusted based on the standard stability coefficient and the combustion stability coefficient of the current boiler to determine the final combustion optimization strategy.

[0053] In some embodiments of the present application, the judgment module determines the combustion stability coefficient of the current boiler based on the boiler combustion thermal imaging data, including: segmenting the boiler combustion thermal imaging data to obtain a number of combustion image blocks, and obtaining the pixel value of each pixel point in the combustion image block; determining the average pixel value of the combustion image block based on the pixel value of each pixel point, calculating the difference between the average pixel value of the combustion image block and the average pixel value of the remaining combustion image blocks within an 8-neighborhood range, and establishing a combustion direction image based on the difference between the average pixel value of the combustion image block and the average pixel value of the remaining combustion image blocks within an 8-neighborhood range; calculating the degree of each combustion image block in the combustion direction image, obtaining the average value of the pixel value difference between each combustion image block and the adjacent combustion image blocks in the combustion direction image, multiplying the average value of the pixel value difference by the corresponding degree to obtain the stability coefficient of the combustion image block; calculating the average value of the stability coefficients of all combustion image blocks in the combustion direction image to obtain the combustion stability coefficient of the boiler.

[0054] In this embodiment, the boiler combustion thermal imaging data is divided into several small image blocks according to the size of the thermal imaging data, and the combustion direction image is established by the difference between the average pixel value of the combustion image block and the average pixel values ​​of the remaining combustion image blocks within the 8-neighborhood range. The degree of each combustion image block is the number of remaining combustion image blocks connected to the combustion image block. The combustion stability coefficient of the boiler is calculated by multiplying the average value of the pixel value difference of each combustion image block by the corresponding degree. The larger the value, the greater the temperature volatility of the boiler combustion.

[0055] In some embodiments of the present application, the burning direction image is established based on the difference between the average pixel values ​​of the burning image block and the remaining burning image blocks within an 8-neighborhood range, including: screening out two burning image blocks whose average pixel value difference is greater than a first preset threshold, connecting the two burning image blocks greater than the first preset threshold to obtain a burning direction image; merging adjacent burning image blocks that are not connected to the remaining burning image blocks, and splicing the merged burning image blocks to obtain a burning direction image.

[0056] In this embodiment, by screening two combustion image blocks whose average pixel value difference is greater than a first preset threshold, two combustion image blocks with a large temperature difference are obtained and connected, and the unconnected combustion image blocks are merged to obtain a combustion direction image. The combustion direction image can be used to more intuitively confirm the temperature fluctuation of boiler combustion.

[0057] In some embodiments of the present application, the judgment module judges whether combustion optimization is needed based on the combustion stability coefficient of the current boiler, including: obtaining a preset combustion allowable coefficient, calculating the difference between the preset combustion allowable coefficient and the combustion stability coefficient; judging whether the difference between the preset combustion allowable coefficient and the combustion stability coefficient is greater than a second preset threshold value, if the difference between the preset combustion allowable coefficient and the combustion stability coefficient is greater than the second preset threshold value, judging that the boiler needs to be optimized for combustion; if the difference between the preset combustion allowable coefficient and the combustion stability coefficient is less than or equal to the second preset threshold value, judging that the boiler does not need to be optimized for combustion.

[0058] In this embodiment, whether the boiler needs combustion optimization is determined by presetting the difference between the combustion permissible coefficient and the combustion stability coefficient, so as to achieve dynamic adjustment of the boiler combustion strategy.

[0059] In some embodiments of the present application, the strategy module determines the current combustion optimization strategy based on the current boiler operation data and operation load, including: obtaining the boiler historical operation database, determining the boiler historical operation parameters and operation load based on the boiler historical operation database; establishing a sample data set based on the boiler historical operation parameters and operation load, and randomly selecting k initial clustering centers of the sample data set; calculating the Euclidean distance from the sample value in the sample data set to the initial clustering center, and dividing each sample data into corresponding partitions based on the Euclidean distance from the sample value in the sample data set to the initial clustering center; calculating the average value of the sample data in each partition, and re-determining the clustering center based on the average value of the sample data in each partition; repeatedly iterating the above steps until the clustering center no longer changes or the number of iterations reaches a preset iteration threshold, and obtaining k final clustering centers; determining the standard operation data and operation load of each cluster partition in the historical operation database based on the final clustering center, establishing a combustion optimization strategy model based on the standard operation data and operation load of each cluster partition, and determining the current combustion optimization strategy based on the combustion optimization strategy model.

[0060] In some embodiments of the present application, a combustion optimization strategy model is established based on the standard operating data and operating load of each cluster partition, and the current combustion optimization strategy is determined based on the combustion optimization strategy model, including: determining the combustion optimization strategy corresponding to the standard operating data and operating load based on the boiler historical operation database, and establishing a training sample set based on the standard operating data and operating load and the corresponding combustion optimization strategy; establishing an initial combustion optimization strategy model, training the initial combustion optimization strategy model based on the training sample set to obtain a trained combustion optimization strategy model; and inputting the current boiler operating data and operating load into the trained combustion optimization strategy model to obtain the current combustion optimization strategy.

[0061] In this embodiment, the historical operating parameters of the boiler and the corresponding operating loads are clustered based on the k-means clustering algorithm to obtain standard operating data and operating loads under various operating conditions. An initial combustion optimization strategy model is established through a deep learning neural network model. The initial combustion optimization strategy model is trained with the standard operating data and operating load, and the current boiler operating data and operating load are input into the trained combustion optimization strategy model to obtain the current combustion optimization strategy.

[0062] In some embodiments of the present application, the optimization module determines a standard stability coefficient according to the current combustion optimization strategy, including: obtaining standard operating data of each cluster partition, determining the combustion thermal imaging data corresponding to the standard operating data of each cluster partition according to the boiler historical operation database, and calculating the degree of matching between the combustion thermal imaging data corresponding to the standard operating data and the preset optimal combustion thermal imaging data; determining the optimal stability coefficient according to the current combustion optimization strategy, and correcting the optimal stability coefficient according to the degree of matching between the combustion thermal imaging data corresponding to the standard operating data and the preset optimal combustion thermal imaging data to obtain the standard stability coefficient.

[0063] In this embodiment, preset optimal combustion thermal imaging data is established through modeling software, and the combustion thermal imaging data corresponding to the standard operating data of each cluster partition is used to calculate the degree of matching between the combustion thermal imaging data corresponding to the standard operating data of each cluster partition and the preset optimal combustion thermal imaging data, and the optimal stability coefficient of the current combustion optimization strategy is corrected to obtain the standard stability coefficient.

[0064] In some embodiments of the present application, the optimal stability coefficient is corrected according to the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data to obtain the standard stability coefficient, including:

[0065] The optimal stability coefficient is corrected according to the stability coefficient correction formula, and the stability coefficient correction formula is specifically:

[0066]

[0067] Among them, S α is the standard stability factor, S o is the optimal stability coefficient, M o is the preset standard matching degree, M α is the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data, and exp is the natural exponential function.

[0068] In this embodiment, the optimal stability coefficient is corrected by the difference between the preset standard matching degree and the matching degree between the combustion thermal imaging data corresponding to the standard operating data and the preset optimal combustion thermal imaging data. The larger the difference, the larger the corresponding standard stability coefficient.

[0069] In some embodiments of the present application, the optimization module determines the final combustion optimization strategy based on the standard stability coefficient and the combustion stability coefficient of the current boiler, including: calculating the difference between the standard stability coefficient and the current combustion stability coefficient, determining the optimization adjustment speed based on the difference between the standard stability coefficient and the current combustion stability coefficient, and determining the final combustion optimization strategy based on the optimization adjustment speed.

[0070] In this embodiment, a mapping table of stability coefficient differences and corresponding optimization adjustment speeds is preset. The optimization speed of the boiler is adjusted by the difference between the standard stability coefficient and the current combustion stability coefficient. The larger the difference, the higher the corresponding optimization adjustment speed, which makes the combustion optimization adjustment effect of the boiler better and effectively improves the thermal efficiency of the boiler.

[0071] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a boiler intelligent combustion optimization control method, comprising:

[0072] S101, obtaining boiler combustion thermal imaging data, determining the combustion stability coefficient of the current boiler according to the boiler combustion thermal imaging data, and judging whether combustion optimization is required according to the combustion stability coefficient of the current boiler;

[0073] S102, if combustion optimization is required, the current boiler operation data and operation load are obtained, and the current combustion optimization strategy is determined according to the current boiler operation data and operation load;

[0074] S103, determining a standard stability coefficient according to the current combustion optimization strategy, and determining a final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler.

[0075] By applying the above technical solutions, the present invention uses a judgment module to obtain boiler combustion thermal imaging data, determine the combustion stability coefficient of the current boiler according to the boiler combustion thermal imaging data, and judge whether combustion optimization is needed according to the combustion stability coefficient of the current boiler; a strategy module is used to obtain the current boiler operation data and operation load if combustion optimization is needed, and determine the current combustion optimization strategy according to the current boiler operation data and operation load; an optimization module is used to determine the standard stability coefficient according to the current combustion optimization strategy, and determine the final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler. The present invention can accurately monitor the combustion state during the operation of the boiler, and formulate a combustion optimization strategy in time according to the combustion state, so that the boiler can maintain stable combustion.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A boiler intelligent combustion optimization control system, characterized in that: include: A judgment module is used to obtain boiler combustion thermal imaging data, determine the combustion stability coefficient of the current boiler according to the boiler combustion thermal imaging data, and judge whether combustion optimization is needed according to the combustion stability coefficient of the current boiler; The strategy module is used to obtain the current boiler operation data and operation load if combustion optimization is required, and determine the current combustion optimization strategy based on the current boiler operation data and operation load; The optimization module is used to determine the standard stability coefficient according to the current combustion optimization strategy, and determine the final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler.

2. The intelligent boiler combustion optimization control system according to claim 1 is characterized in that: The judgment module determines the combustion stability coefficient of the current boiler according to the boiler combustion thermal imaging data, including: Segment the boiler combustion thermal imaging data to obtain a number of combustion image blocks, and obtain the pixel value of each pixel in the combustion image block; Determine the average pixel value of the burning image block according to the pixel value of each pixel point, calculate the difference between the average pixel value of the burning image block and the average pixel value of the remaining burning image blocks within the 8-neighborhood range, and establish a burning direction image according to the difference between the average pixel value of the burning image block and the average pixel value of the remaining burning image blocks within the 8-neighborhood range; Calculate the degree of each burning image block in the burning direction image, obtain the average value of the pixel value difference between each burning image block and the adjacent burning image block in the burning direction image, multiply the average value of the pixel value difference by the corresponding degree, and obtain the stability coefficient of the burning image block; The average value of the stability coefficients of all combustion image blocks in the combustion direction image is calculated to obtain the combustion stability coefficient of the boiler.

3. The intelligent boiler combustion optimization control system according to claim 2 is characterized in that: The method of establishing a burning direction image according to the difference between the burning image block and the average pixel value of the remaining burning image blocks within the 8-neighborhood range includes: Screen out two burning image blocks whose average pixel value difference is greater than a first preset threshold, connect the two burning image blocks whose average pixel values ​​are greater than the first preset threshold, and obtain a burning direction image; The adjacent burning image blocks that are not connected to the other burning image blocks are merged, and the merged burning image blocks are spliced ​​to obtain a burning direction image.

4. The intelligent boiler combustion optimization control system according to claim 3 is characterized in that: The judging module judges whether combustion optimization is required according to the combustion stability coefficient of the current boiler, including: Obtaining a preset combustion allowable coefficient, and calculating a difference between the preset combustion allowable coefficient and a combustion stability coefficient; Determine whether the difference between the preset combustion permissible coefficient and the combustion stability coefficient is greater than a second preset threshold value, and if the difference between the preset combustion permissible coefficient and the combustion stability coefficient is greater than the second preset threshold value, determine that the boiler needs to be optimized for combustion; If the difference between the preset combustion permissible coefficient and the combustion stability coefficient is less than or equal to the second preset threshold, it is determined that the boiler does not need to be optimized for combustion.

5. The intelligent boiler combustion optimization control system according to claim 1 is characterized in that: The strategy module determines the current combustion optimization strategy according to the current boiler operation data and operation load, including: Obtain a boiler historical operation database, and determine the boiler historical operation parameters and operation load according to the boiler historical operation database; A sample data set is established based on the historical operating parameters and operating load of the boiler, and k initial clustering centers of the sample data set are randomly selected; Calculate the Euclidean distance from the sample value in the sample data set to the initial cluster center, and divide each sample data into corresponding partitions according to the Euclidean distance from the sample value in the sample data set to the initial cluster center; Calculate the average value of the sample data in each partition, and re-determine the cluster center based on the average value of the sample data in each partition; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset iteration threshold, and obtain k final cluster centers; The standard operation data and operation load of each cluster partition in the historical operation database are determined according to the final cluster center, a combustion optimization strategy model is established according to the standard operation data and operation load of each cluster partition, and the current combustion optimization strategy is determined according to the combustion optimization strategy model.

6. The intelligent boiler combustion optimization control system according to claim 5 is characterized in that: The method of establishing a combustion optimization strategy model according to the standard operation data and operation load of each cluster partition and determining the current combustion optimization strategy according to the combustion optimization strategy model includes: Determine the combustion optimization strategy corresponding to the standard operation data and the operation load according to the boiler historical operation database, and establish a training sample set according to the standard operation data and the operation load and the corresponding combustion optimization strategy; An initial combustion optimization strategy model is established, and the initial combustion optimization strategy model is trained according to a training sample set to obtain a trained combustion optimization strategy model; The current boiler operation data and operation load are input into the trained combustion optimization strategy model to obtain the current combustion optimization strategy.

7. The intelligent boiler combustion optimization control system according to claim 6 is characterized in that: The optimization module determines the standard stability coefficient according to the current combustion optimization strategy, including: Obtaining standard operation data of each cluster partition, determining the combustion thermal imaging data corresponding to the standard operation data of each cluster partition according to the boiler historical operation database, and calculating the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data; The optimal stability coefficient is determined according to the current combustion optimization strategy, and the optimal stability coefficient is corrected according to the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data to obtain the standard stability coefficient.

8. The intelligent boiler combustion optimization control system according to claim 7 is characterized in that: The optimal stability coefficient is corrected according to the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data to obtain the standard stability coefficient, including: The optimal stability coefficient is corrected according to the stability coefficient correction formula, and the stability coefficient correction formula is specifically: Among them, S α is the standard stability factor, S o is the optimal stability coefficient, M o is the preset standard matching degree, M α is the matching degree between the combustion thermal imaging data corresponding to the standard operation data and the preset optimal combustion thermal imaging data, and exp is the natural exponential function.

9. The intelligent boiler combustion optimization control system according to claim 1 is characterized in that: The optimization module determines the final combustion optimization strategy according to the standard stability coefficient and the combustion stability coefficient of the current boiler, including: The difference between the standard stability coefficient and the current combustion stability coefficient is calculated, the optimization adjustment speed is determined according to the difference between the standard stability coefficient and the current combustion stability coefficient, and the final combustion optimization strategy is determined according to the optimization adjustment speed.

10. A boiler intelligent combustion optimization control method, characterized in that: include: Obtain boiler combustion thermal imaging data, determine the combustion stability coefficient of the current boiler based on the boiler combustion thermal imaging data, and determine whether combustion optimization is needed based on the combustion stability coefficient of the current boiler; If combustion optimization is required, the current boiler operation data and operation load are obtained, and the current combustion optimization strategy is determined based on the current boiler operation data and operation load; The standard stability coefficient is determined according to the current combustion optimization strategy, and the final combustion optimization strategy is determined according to the standard stability coefficient and the combustion stability coefficient of the current boiler.

Images