Combustion control method and system based on internet of things feedback control

Abstract

The application discloses a kind of based on feedback control of Internet of Things combustion control method and system, it is related to computer control technical field, the method includes: by obtaining preset heating surface basic information, including heating area information, boiler capacity information and heating cycle information;Match expected heat exchange amount;According to heat resistance temperature sensor, upload preset time granularity of preset heating surface smoke temperature record data, wall temperature record data and steam-water heating record data;Calculate first contamination coefficient;Obtain combustion control parameter;The combustion control parameter is optimized and designed, generates combustion control parameter optimization result, carries out boiler combustion control.The traditional combustion control of boiler in prior art exists that the degree of burning is not high, and then high-alkali coal is wasted, finally leading to the problem of low utilization rate of high-alkali coal.The intelligent degree of the target of improving the combustion control of boiler unit is realized, the degree of burning of coal in the boiler is improved, and the effect of maximizing the utilization of coal resources is realized.

Description

Technical Field

[0001] This invention relates to the field of computer control technology, and in particular to a combustion control method and system based on Internet of Things (IoT) feedback control. Background Technology

[0002] With the rapid development of computer science and technology, various industries are leveraging computer technology to reform their traditional production processes and equipment control through informatization, striving to replace traditional manual operations with intelligent technology to improve enterprise productivity and competitiveness. In the field of boiler combustion control, the focus is shifting from traditional manual experience-based control to intelligent dynamic regulation. Existing technologies using traditional control schemes for boiler regulation suffer from incomplete coal combustion, leading to waste and underutilization of coal resources. For example, current boilers cannot achieve 100% combustion of high-alkali coal from the Zhundong region; most units can only maintain a blending ratio of 50-70%, while some advanced units can reach 80-90%. Once a certain critical value is exceeded, severe slagging and fouling occur on the boiler's water-cooled walls, partitions, superheaters, and reheaters, leading to frequent problems such as excessive wall temperatures, tube ruptures, flue blockages, and coke shedding, severely restricting the development and utilization of high-alkali coal in various regions. Therefore, researching intelligent dynamic regulation of boiler combustion is urgently needed.

[0003] However, existing technologies typically rely on boiler control experience and subjective analysis by technicians for boiler combustion control. When using these control schemes to burn high-alkali coal, the combustion degree is not high, resulting in waste of high-alkali coal and ultimately leading to low utilization rate of high-alkali coal, which may even affect its development rate. Summary of the Invention

[0004] The purpose of this invention is to provide a combustion control method and system based on Internet of Things feedback control, in order to solve the technical problem that the combustion control of boilers is usually based on boiler control experience and subjective analysis by technicians. When using such control schemes to burn high-alkali coal, the combustion degree is not high, which leads to waste of high-alkali coal and ultimately results in low utilization rate of high-alkali coal, and even affects its development rate.

[0005] In view of the above problems, the present invention provides a combustion control method and system based on Internet of Things feedback control.

[0006] In a first aspect, the present invention provides a combustion control method based on Internet of Things (IoT) feedback control. The method is implemented through a combustion control system based on IoT feedback control. The method includes: acquiring basic information of a preset heating surface, wherein the basic information of the preset heating surface includes heating area information, boiler capacity information, and heating cycle information; matching the desired heat exchange based on the heating area information, the boiler capacity information, and the heating cycle information; uploading flue gas temperature recording data, wall temperature recording data, and steam-water heating recording data of the preset heating surface at a preset time granularity based on a heat-resistant temperature sensor; calculating a first fouling coefficient based on the flue gas temperature recording data, the wall temperature recording data, and the steam-water heating recording data; acquiring combustion control parameters; optimizing the combustion control parameters based on the first fouling coefficient and the desired heat exchange, generating an optimized combustion control parameter result; and performing boiler combustion control based on the optimized combustion control parameter result.

[0007] Secondly, the present invention also provides a combustion control system based on Internet of Things (IoT) feedback control, used to execute a combustion control method based on IoT feedback control as described in the first aspect, wherein the system includes: a first acquisition module, used to acquire basic information of a preset heating surface, wherein the basic information of the preset heating surface includes heating area information, boiler capacity information, and heating cycle information; an intelligent matching module, used to match the desired heat exchange based on the heating area information, the boiler capacity information, and the heating cycle information; an intelligent uploading module, used to upload flue gas temperature recording data, wall temperature recording data, and steam-water heating recording data of the preset heating surface at a preset time granularity based on a heat-resistant temperature sensor; an intelligent calculation module, used to calculate a first fouling coefficient based on the flue gas temperature recording data, the wall temperature recording data, and the steam-water heating recording data; a second acquisition module, used to acquire combustion control parameters; an intelligent generation module, used to optimize the combustion control parameters based on the first fouling coefficient and the desired heat exchange, and generate combustion control parameter optimization results; and an intelligent execution module, used to perform boiler combustion control based on the combustion control parameter optimization results.

[0008] One or more technical solutions provided in this invention have at least the following technical effects or advantages:

[0009] By acquiring basic information about a preset heating surface, including heating area, boiler capacity, and heating cycle information; matching the desired heat exchange capacity based on the heating area, boiler capacity, and heating cycle information; uploading flue gas temperature, wall temperature, and steam-water heating data at a preset time granularity for the preset heating surface using a heat-resistant temperature sensor; calculating a first fouling coefficient based on the flue gas temperature, wall temperature, and steam-water heating data; obtaining combustion control parameters; optimizing the combustion control parameters based on the first fouling coefficient and the desired heat exchange capacity to generate optimized combustion control parameter results; and performing boiler combustion control based on the optimized combustion control parameter results. By collecting and analyzing basic information about the boiler's preset heating surface, the goal of providing computational data for subsequent analysis to determine the desired heat exchange capacity of the corresponding boiler is achieved, thus improving the accuracy of the matched desired heat exchange capacity. By monitoring real-time recorded data from the preset heating surface using intelligent devices, flue gas temperature, wall temperature, and steam-water heating data at preset time granularities are obtained. This achieves the goal of providing a comprehensive and specific data foundation for subsequent analysis of the real-time fouling status of the preset heating surface, thus improving the effectiveness and real-world accuracy of the first fouling coefficient. Based on the first fouling coefficient and the expected heat transfer, the boiler's combustion control parameters are specifically adjusted and optimized, achieving the technical goal of improving the intelligence level of boiler control and optimizing boiler combustion control to achieve optimal boiler unit operation. This also achieves the technical goal of improving the intelligence level of boiler unit combustion control, increasing the combustion intensity of coal within the boiler, and maximizing the utilization of coal resources.

[0010] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of a combustion control method based on Internet of Things feedback control according to the present invention;

[0013] Figure 2This is a schematic diagram of the process for obtaining the desired heat exchange in a combustion control method based on Internet of Things feedback control according to the present invention.

[0014] Figure 3 This is a schematic diagram of the process for calculating the first fouling coefficient in a combustion control method based on Internet of Things feedback control according to the present invention.

[0015] Figure 4 This is a schematic diagram of the process for selecting the optimization results of the combustion control parameters in a combustion control method based on Internet of Things feedback control according to the present invention.

[0016] Figure 5 This is a schematic diagram of the structure of a combustion control system based on Internet of Things feedback control according to the present invention.

[0017] Explanation of reference numerals in the attached figures:

[0018] The system consists of a first acquisition module M100, an intelligent matching module M200, an intelligent upload module M300, an intelligent calculation module M400, a second acquisition module M500, an intelligent generation module M600, and an intelligent execution module M700. Detailed Implementation

[0019] This invention provides a combustion control method and system based on Internet of Things (IoT) feedback control. It solves the technical problem in existing technologies where boiler combustion control is typically based on boiler control experience and subjective analysis by technicians. This often results in low combustion intensity when using control schemes for high-alkali coal, leading to waste of high-alkali coal and ultimately low utilization rates, even impacting its exploitation rate. The invention achieves the technical goal of improving the intelligence level of boiler unit combustion control, thereby increasing the combustion intensity of coal within the boiler and maximizing the utilization of coal resources.

[0020] The acquisition, storage, use, and processing of data in the technical solution of this invention all comply with the relevant provisions of national laws and regulations.

[0021] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0022] Example 1

[0023] Please see the appendix Figure 1This invention provides a combustion control method based on Internet of Things (IoT) feedback control. The method is applied to a combustion control system based on IoT feedback control and specifically includes the following steps:

[0024] Step S100: Obtain the basic information of the preset heating surface, wherein the basic information of the preset heating surface includes heating area information, boiler capacity information and heating cycle information;

[0025] Specifically, the aforementioned combustion control method based on IoT feedback control is applied to a combustion control system based on IoT feedback control. It can intelligently and dynamically optimize the boiler's combustion control parameters by real-time monitoring of the actual situation of the boiler's corresponding preset heating surface and combining this with the basic information of the preset heating surface. This ensures that the boiler unit operates under optimal parameters, ultimately achieving the goal of maximizing coal combustion and utilization within the boiler. First, multi-dimensional feature collection and analysis are performed on the boiler's preset heating surface, including the area of ​​the preset heating surface, the boiler's capacity, and the boiler's heating cycle. For example, boiler A has a heating area of ​​5 square meters and a capacity of 30 cubic meters. Based on historical heating data, the boiler's heating cycle is calculated to be 40 minutes. By collecting and analyzing basic information about the boiler's preset heating surface, the goal of providing calculation data for subsequent analysis to determine the expected heat exchange of the corresponding boiler is achieved, thus improving the accuracy of the matched expected heat exchange.

[0026] Step S200: Match the desired heat exchange capacity based on the heated area information, the boiler capacity information, and the heating cycle information;

[0027] Further details are attached. Figure 2 As shown, step S200 of the present invention includes:

[0028] Step S210: Determine whether the preset update cycle is met;

[0029] Step S220: If satisfied, based on the Internet of Things, obtain the first boiler combustion plant, the second boiler combustion plant, and so on up to the Nth boiler combustion plant;

[0030] Step S230: Upload a quad data set through the first boiler combustion plant, the second boiler combustion plant up to the Nth boiler combustion plant, wherein the quad data set includes the heating area, boiler capacity, heating cycle and expected heat exchange.

[0031] Step S240: Update the quaternary parameter decision database according to the quaternary data set, input the heating area information, the boiler capacity information and the heating cycle information, and obtain the expected heat exchange.

[0032] Specifically, based on the collected relevant index parameters of the preset heating surface on the boiler, the combustion control system automatically matches the expected heat exchange of the boiler. First, it determines whether the heating cycle information meets the preset update cycle. When the result shows that it meets the preset update cycle, the combustion control system automatically matches and acquires boiler plants based on the Internet of Things (IoT), including acquiring the first boiler combustion plant, the second boiler combustion plant, and so on up to the Nth boiler combustion plant. Then, it sequentially analyzes the information of the first boiler combustion plant, the second boiler combustion plant, and so on up to the Nth boiler combustion plant. That is, it sequentially collects the relevant basic characteristics of the boilers in each boiler combustion plant, including boiler capacity, heating area, and heating cycle, and further sequentially matches the expected heat exchange of the boilers in each boiler combustion plant. Then, it uploads the characteristic parameters of each boiler combustion plant to obtain the uploaded four-element data set, which includes heating area, boiler capacity, heating cycle, and expected heat exchange. Finally, it automatically and dynamically updates the four-element parameter decision database based on the real-time uploaded four-element data set, and intelligently inputs the heating area information, the boiler capacity information, and the heating cycle information to obtain the corresponding expected heat exchange.

[0033] By analyzing the relevant characteristics of boilers in the combustion boiler plant, the corresponding expected heat exchange is matched, thereby achieving the technical goal of improving the targeting of expected heat exchange matching. This further achieves the effect of providing accurate expected heat exchange data for subsequent optimization of boiler combustion control parameters.

[0034] Step S300: Based on the heat-resistant temperature sensor, upload the flue gas temperature recording data, wall temperature recording data, and steam and water heating recording data of the preset time granularity of the preset heated surface;

[0035] Step S400: Calculate the first fouling coefficient based on the smoke temperature recording data, the wall temperature recording data, and the steam and water heating recording data;

[0036] Further details are attached. Figure 3 As shown, step S400 of the present invention includes:

[0037] Step S410: Calculate the first absorption-to-desorption ratio coefficient based on the smoke temperature recording data and the wall temperature recording data;

[0038] Step S420: Calculate the second absorption / desorption ratio coefficient based on the wall temperature recording data and the steam / water heating recording data;

[0039] Step S430: Calculate the first contamination coefficient based on the first absorption-desorption ratio coefficient and the second absorption-desorption ratio coefficient.

[0040] Furthermore, the present invention also includes the following steps:

[0041] Step S441: Determine whether the first contamination coefficient meets the contamination coefficient threshold range;

[0042] Step S442: If the conditions are not met, generate an abnormal pollution coefficient warning message; if the conditions are met, load the combustion control parameters.

[0043] Specifically, the heat-resistant temperature sensor is an intelligent device capable of intelligently sensing boiler temperature in real time. This intelligent device is made of heat-resistant material and is used for intelligent temperature detection under special high-temperature environments. Furthermore, the heat-resistant temperature sensor is communicatively connected to the combustion control system. Therefore, after the heat-resistant temperature sensor detects the temperature at a corresponding location in real time, it synchronously transmits the real-time temperature to the combustion control system for intelligent analysis and processing. Firstly, the heat-resistant temperature sensor dynamically detects and transmits in real-time the flue gas temperature recording data, wall temperature recording data, and steam-water heating recording data of the preset heating surfaces of the boiler within the combustion boiler plant at preset time granularities to the combustion control system. The heat-resistant temperature sensors are deployed according to actual conditions and include several sensor devices. The flue gas temperature recording data is obtained in real-time by heat-resistant temperature sensors deployed at specific locations on the boiler heating surface, representing the real-time flue gas temperature of the boiler. The wall temperature recording data is obtained in real-time by heat-resistant temperature sensors deployed at specific locations on the boiler heating surface, representing the real-time wall temperature of the boiler. An exemplary approach involves evenly distributing several heat-resistant temperature sensors at 20-centimeter intervals on the boiler wall. Each sensor measures a temperature, and the average of all these temperature readings is calculated to obtain the recorded wall temperature. The recorded steam-water heating temperature is obtained in real-time from heat-resistant temperature sensors positioned at specific locations on the boiler's heating surface, representing the real-time steam-water heating temperature. By monitoring the real-time recorded data of the preset heating surface using intelligent equipment, flue gas temperature, wall temperature, and steam-water heating recorded data at a preset time granularity are obtained. This achieves the goal of providing a comprehensive and specific data foundation for subsequent analysis of the real-time fouling status of the preset heating surface, thereby improving the effectiveness and accuracy of the first fouling coefficient.

[0044] Furthermore, based on the flue gas temperature recording data, the wall temperature recording data, and the steam-water heating recording data, the real-time fouling status of the preset heating surface is analyzed, i.e., the first fouling coefficient is calculated. For example, when a boiler burns coal, its unit can only maintain a co-firing ratio of 50-70%. Once a certain critical value is exceeded, such as 65%, severe slagging and fouling will occur on the boiler's water-cooled walls, partitions, superheaters, reheaters, and other heating surfaces. This can even lead to problems such as excessive wall temperature, tube rupture, flue blockage, and coke shedding, severely restricting the development and utilization of coal. Next, based on the flue gas temperature recording data and the wall temperature recording data, a first absorption / desorption ratio coefficient is calculated, and based on the wall temperature recording data and the steam-water heating recording data, a second absorption / desorption ratio coefficient is calculated. Finally, based on the first absorption / desorption ratio coefficient and the second absorption / desorption ratio coefficient, the first fouling coefficient is calculated.

[0045] Furthermore, the system determines whether the first fouling coefficient of the boiler's preset heating surface falls within the fouling coefficient threshold range pre-set by relevant technical personnel based on a comprehensive analysis of the boiler manufacturer and actual combustion control conditions. If the first fouling coefficient does not meet the threshold, the combustion control system automatically generates an abnormal fouling coefficient warning, indicating that the boiler's preset heating surface is experiencing severe fouling and slagging. To ensure the safe and stable operation of the boiler, the system should issue a warning, and relevant personnel should perform targeted maintenance and upkeep. An example of this is an audible alarm. However, if the first fouling coefficient meets the threshold, it indicates that the boiler's combustion control is currently normal and stable, and therefore the system automatically loads the boiler's combustion control parameters at this time.

[0046] Through intelligent detection by heat-resistant temperature sensors, the flue gas temperature, wall temperature, and steam-water heating data of the preset heating surfaces are obtained, realizing the automatic monitoring target of boiler coking. This breaks through the limitations of traditional manual judgment and adjustment. Based on intelligent detection data, the safety of the heating surfaces is intelligently evaluated by the fouling coefficient of the heating surfaces, achieving the technical effect of improving the safe, stable, and reliable operation of boiler combustion control.

[0047] Step S500: Obtain combustion control parameters;

[0048] Step S600: Based on the first fouling coefficient and the expected heat exchange, optimize the combustion control parameters and generate combustion control parameter optimization results;

[0049] Further details are attached. Figure 4 As shown, step S600 of the present invention includes:

[0050] Step S610: Based on the combustion control parameters, obtain the flue gas temperature constraint range, the flame center position constraint range, the conveying air volume constraint range, and the conveying coal flow rate constraint range;

[0051] Step S620: Construct the fitness function;

[0052] Furthermore, the present invention also includes the following steps:

[0053] The fitness function is:

[0054]

[0055] Step S621: Where, D k f represents the fitness of the k-th group of combustion control log data. k c represents the frequency of occurrence of the k-th group of combustion control log data. k The control cost of the k-th group of combustion control log data is represented by M, the total number of groups of combustion control log data traversed, and α and β, which are the bias indices of the frequency and cost terms, respectively, and are greater than or equal to 0.

[0056] Step S630: Traverse the flue gas temperature constraint interval, the flame center position constraint interval, the conveying air volume constraint interval, and the conveying coal flow rate constraint interval, and collect the combustion control log dataset based on the first fouling coefficient and the expected heat exchange.

[0057] Step S640: Based on the fitness function, filter the combustion control parameter optimization results from the combustion control log dataset.

[0058] Furthermore, the present invention also includes the following steps:

[0059] Step S641: Set the frequency term bias index and the cost term bias index according to the fitness function;

[0060] Step S642: Obtain the kth set of combustion control log data based on the combustion control log dataset;

[0061] Step S643: Based on the frequency term bias index and the cost term bias index, input the kth group of combustion control log data into the fitness function to obtain the kth fitness;

[0062] Step S644: Determine whether the k-th fitness is greater than or equal to the (k-1)-th fitness;

[0063] Step S645: If it is less than, add the kth group of combustion control log data to the elimination data group, and add the (k-1)th group of combustion control log data to the winning data group to continue the iteration; if it is greater than or equal to, add the (k-1)th group of combustion control log data to the elimination data group, and add the kth group of combustion control log data to the winning data group to continue the iteration.

[0064] Step S646: When k satisfies M, obtain the optimization result of the combustion control parameters according to the winning data set.

[0065] Specifically, the combustion control parameters refer to the parameters set by the boiler unit when actually controlling the combustion of coal. After calculating the first fouling coefficient and the expected heat exchange, the combustion control system dynamically optimizes its current combustion control parameters, and the optimized unit control parameters are the combustion control parameter optimization results.

[0066] First, based on the current combustion control parameters of the boiler, the following constraint intervals are extracted sequentially: flue gas temperature constraint interval, flame center position constraint interval, conveying air volume constraint interval, and conveying coal flow rate constraint interval. Then, a fitness function is constructed, which is:

[0067]

[0068] Among them, D k f represents the fitness of the k-th group of combustion control log data. k c represents the frequency of occurrence of the k-th group of combustion control log data. k The control cost of the k-th group of combustion control log data is represented by M, the total number of groups of combustion control log data traversed, and α and β, which are the bias indices of the frequency and cost terms, respectively, and are greater than or equal to 0.

[0069] Furthermore, the combustion control parameters of the boiler are collected by traversing the flue gas temperature constraint interval, the flame center position constraint interval, the conveying air volume constraint interval, and the conveying coal flow rate constraint interval, and based on the aforementioned calculations, the first fouling coefficient and the expected heat exchange are obtained, thus acquiring a combustion control log dataset. Finally, the optimization results of the combustion control parameters are obtained from the combustion control log dataset according to the fitness function. Specifically, a frequency term bias index and a cost term bias index are set based on the fitness function, and the k-th group of combustion control log data is obtained based on the combustion control log dataset. Next, based on the frequency term bias index and the cost term bias index, the k-th group of combustion control log data is input into the fitness function to obtain the k-th fitness. Then, it is determined whether the k-th fitness is greater than or equal to the (k-1)-th fitness. When the k-th fitness is less than the (k-1)-th fitness, the combustion control system automatically adds the k-th group of combustion control log data to the elimination data group and adds the (k-1)-th group of combustion control log data to the winning data group for further iteration. However, when the k-th fitness is greater than or equal to the (k-1)-th fitness, the (k-1)-th group of combustion control log data is added to the eliminated data group, and the k-th group of combustion control log data is added to the winning data group for further iteration. This process continues until k satisfies M, at which point the combustion control parameter optimization result is obtained based on the winning data group.

[0070] Step S700: Perform boiler combustion control based on the optimization results of the combustion control parameters.

[0071] Specifically, the boiler is dynamically controlled and adjusted based on the optimized combustion control parameters, achieving the goal of targeted boiler control optimization. This achieves the technical objective of improving the intelligence level of boiler unit combustion control, and realizes the technical effect of increasing the combustion rate of coal in the boiler, thereby maximizing the utilization of coal resources.

[0072] In summary, the combustion control method based on Internet of Things feedback control provided by this invention has the following technical effects:

[0073] By acquiring basic information about a preset heating surface, including heating area, boiler capacity, and heating cycle information; matching the desired heat exchange capacity based on the heating area, boiler capacity, and heating cycle information; uploading flue gas temperature, wall temperature, and steam-water heating data at a preset time granularity for the preset heating surface using a heat-resistant temperature sensor; calculating a first fouling coefficient based on the flue gas temperature, wall temperature, and steam-water heating data; obtaining combustion control parameters; optimizing the combustion control parameters based on the first fouling coefficient and the desired heat exchange capacity to generate optimized combustion control parameter results; and performing boiler combustion control based on the optimized combustion control parameter results. By collecting and analyzing basic information about the boiler's preset heating surface, the goal of providing computational data for subsequent analysis to determine the desired heat exchange capacity of the corresponding boiler is achieved, thus improving the accuracy of the matched desired heat exchange capacity. By monitoring real-time recorded data from the preset heating surface using intelligent devices, flue gas temperature, wall temperature, and steam-water heating data at preset time granularities are obtained. This achieves the goal of providing a comprehensive and specific data foundation for subsequent analysis of the real-time fouling status of the preset heating surface, thus improving the effectiveness and real-world accuracy of the first fouling coefficient. Based on the first fouling coefficient and the expected heat transfer, the boiler's combustion control parameters are specifically adjusted and optimized, achieving the technical goal of improving the intelligence level of boiler control and optimizing boiler combustion control to achieve optimal boiler unit operation. This also achieves the technical goal of improving the intelligence level of boiler unit combustion control, increasing the combustion intensity of coal within the boiler, and maximizing the utilization of coal resources.

[0074] Example 2

[0075] Based on the combustion control method based on IoT feedback control in the foregoing embodiments, and using the same inventive concept, this invention also provides a combustion control system based on IoT feedback control. Please refer to the appendix. Figure 5 The system includes:

[0076] The first acquisition module M100 is used to acquire the basic information of the preset heating surface, wherein the basic information of the preset heating surface includes heating area information, boiler capacity information and heating cycle information.

[0077] The intelligent matching module M200 is used to match the desired heat exchange based on the heat transfer area information, the boiler capacity information, and the heating cycle information.

[0078] The intelligent upload module M300 is used to upload flue gas temperature record data, wall temperature record data, and steam and water heating record data of a preset time granularity for the preset heated surface, based on the heat-resistant temperature sensor.

[0079] The intelligent calculation module M400 is used to calculate the first fouling coefficient based on the smoke temperature recording data, the wall temperature recording data, and the steam and water heating recording data;

[0080] The second acquisition module M500 is used to acquire combustion control parameters;

[0081] The intelligent generation module M600 is used to optimize the combustion control parameters based on the first fouling coefficient and the expected heat exchange, and generate the combustion control parameter optimization result.

[0082] The intelligent execution module M700 is used to perform boiler combustion control based on the optimization results of the combustion control parameters.

[0083] Furthermore, the intelligent matching module M200 in the system is also used for:

[0084] Determine whether the preset update cycle is met;

[0085] If the conditions are met, based on the Internet of Things, the first boiler combustion plant, the second boiler combustion plant, and so on up to the Nth boiler combustion plant are obtained;

[0086] Through the first boiler combustion plant, the second boiler combustion plant, and up to the Nth boiler combustion plant, a four-data set is uploaded, wherein the four-data set includes the heating area, boiler capacity, heating cycle, and expected heat exchange.

[0087] The quaternary parameter decision database is updated based on the quaternary data set. The heating area information, the boiler capacity information, and the heating cycle information are input to obtain the expected heat exchange.

[0088] Furthermore, the intelligent computing module M400 in the system is also used for:

[0089] Calculate the first absorption-to-desorption ratio coefficient based on the smoke temperature recording data and the wall temperature recording data;

[0090] Calculate the second absorption / desorption ratio coefficient based on the wall temperature record data and the steam / water heating record data;

[0091] The first fouling coefficient is calculated based on the first adsorption / desorption ratio coefficient and the second adsorption / desorption ratio coefficient.

[0092] Furthermore, the intelligent computing module M400 in the system is also used for:

[0093] Determine whether the first contamination coefficient meets the contamination coefficient threshold range;

[0094] If the conditions are not met, an abnormal pollution coefficient warning message is generated; if the conditions are met, the combustion control parameters are loaded.

[0095] Furthermore, the intelligent generation module M600 in the system is also used for:

[0096] Based on the combustion control parameters, obtain the flue gas temperature constraint range, the flame center position constraint range, the conveying air volume constraint range, and the conveying coal flow rate constraint range;

[0097] Construct the fitness function;

[0098] Traverse the flue gas temperature constraint interval, the flame center position constraint interval, the conveying air volume constraint interval, and the conveying coal flow rate constraint interval, and collect a combustion control log dataset based on the first fouling coefficient and the expected heat exchange.

[0099] The optimization results of the combustion control parameters are filtered from the combustion control log dataset according to the fitness function.

[0100] Furthermore, the intelligent generation module M600 in the system is also used for:

[0101] The fitness function is:

[0102]

[0103] Among them, D k f represents the fitness of the k-th group of combustion control log data. k c represents the frequency of occurrence of the k-th group of combustion control log data. k The control cost of the k-th group of combustion control log data is represented by M, the total number of groups of combustion control log data traversed, and α and β, which are the bias indices of the frequency and cost terms, respectively, and are greater than or equal to 0.

[0104] Furthermore, the intelligent generation module M600 in the system is also used for:

[0105] Based on the fitness function, set the frequency term bias index and the cost term bias index;

[0106] Based on the combustion control log dataset, obtain the kth set of combustion control log data;

[0107] Based on the frequency term bias index and the cost term bias index, the kth group of combustion control log data is input into the fitness function to obtain the kth fitness.

[0108] Determine whether the fitness of the kth fitness is greater than or equal to the fitness of the (k-1)th fitness;

[0109] If the value is less than the value, the kth group of combustion control log data is added to the elimination data group, and the (k-1)th group of combustion control log data is added to the winning data group to continue the iteration; if the value is greater than or equal to the value, the (k-1)th group of combustion control log data is added to the elimination data group, and the kth group of combustion control log data is added to the winning data group to continue the iteration.

[0110] When k satisfies M, the optimization result of the combustion control parameters is obtained based on the winning data set.

[0111] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The combustion control method and specific example based on IoT feedback control in Embodiment 1 are also applicable to the combustion control system based on IoT feedback control in this embodiment. Through the foregoing detailed description of the combustion control method based on IoT feedback control, those skilled in the art can clearly understand the combustion control system based on IoT feedback control in this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0112] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0113] Obviously, those skilled in the art can 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 this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A combustion control method based on Internet of Things (IoT) feedback control, characterized in that, include: Obtain basic information of a preset heating surface, wherein the basic information of the preset heating surface includes heating area information, boiler capacity information, and heating cycle information; Based on the heated area information, the boiler capacity information, and the heating cycle information, the desired heat exchange is matched; Based on the heat-resistant temperature sensor, upload the flue gas temperature record data, wall temperature record data, and steam and water heating record data at a preset time granularity for the preset heated surface; Calculate the first fouling coefficient based on the smoke temperature record data, the wall temperature record data, and the steam / water heating record data; Obtain combustion control parameters; Based on the first fouling coefficient and the expected heat exchange, the combustion control parameters are optimized to generate combustion control parameter optimization results; Boiler combustion control is performed based on the optimization results of the combustion control parameters. The step of calculating the first fouling coefficient based on the smoke temperature record data, the wall temperature record data, and the steam / water heating record data includes: Calculate the first absorption-to-desorption ratio coefficient based on the smoke temperature recording data and the wall temperature recording data; Calculate the second absorption / desorption ratio coefficient based on the wall temperature record data and the steam / water heating record data; The first fouling coefficient is calculated based on the first adsorption-desorption ratio coefficient and the second adsorption-desorption ratio coefficient.

2. The method as described in claim 1, characterized in that, The step of matching the desired heat exchange based on the heated area information, the boiler capacity information, and the heating cycle information includes: Determine whether the preset update cycle is met; If the conditions are met, the first boiler combustion plant, the second boiler combustion plant, and so on up to the Nth boiler combustion plant can be obtained based on the Internet of Things. The four-dimensional data set is uploaded through the first boiler combustion plant, the second boiler combustion plant and up to the Nth boiler combustion plant, wherein the four-dimensional data set includes the heating area, boiler capacity, heating cycle and expected heat exchange. The quaternary parameter decision database is updated based on the quaternary data set. The heating area information, the boiler capacity information, and the heating cycle information are input to obtain the expected heat exchange.

3. The method as described in claim 1, characterized in that, include: Determine whether the first contamination coefficient meets the contamination coefficient threshold range; If the conditions are not met, an abnormal contamination coefficient warning will be generated. If satisfied, load the combustion control parameters.

4. The method as described in claim 1, characterized in that, The step of optimizing the combustion control parameters based on the first fouling coefficient and the expected heat exchange to generate optimized combustion control parameter results includes: Based on the combustion control parameters, obtain the flue gas temperature constraint range, the flame center position constraint range, the conveying air volume constraint range, and the conveying coal flow rate constraint range; Construct the fitness function; Traverse the flue gas temperature constraint interval, the flame center position constraint interval, the conveying air volume constraint interval, and the conveying coal flow rate constraint interval, and collect a combustion control log dataset based on the first fouling coefficient and the expected heat exchange. The optimization results of the combustion control parameters are filtered from the combustion control log dataset according to the fitness function.

5. The method as described in claim 4, characterized in that, The fitness function is: ， in, Characterizes the fitness of the k-th group of combustion control log data. Characterizing the frequency of occurrence of the k-th group of combustion control log data, Let M represent the control cost of the k-th group of combustion control log data, and M represent the total number of combustion control log data groups traversed. and An index representing the bias between the frequency and cost terms, and greater than or equal to 0.

6. The method as described in claim 5, characterized in that, The step of filtering the combustion control parameter optimization results from the combustion control log dataset according to the fitness function includes: Based on the fitness function, set the frequency term bias index and the cost term bias index; Based on the combustion control log dataset, obtain the kth set of combustion control log data; Based on the frequency term bias index and the cost term bias index, the kth group of combustion control log data is input into the fitness function to obtain the kth fitness. Determine whether the fitness of the kth fitness is greater than or equal to the fitness of the (k-1)th fitness; If the value is less than the value, the kth group of combustion control log data is added to the elimination data group, and the (k-1)th group of combustion control log data is added to the winning data group to continue the iteration; if the value is greater than or equal to the value, the (k-1)th group of combustion control log data is added to the elimination data group, and the kth group of combustion control log data is added to the winning data group to continue the iteration. When k satisfies M, the optimization result of the combustion control parameters is obtained based on the winning data set.

7. A combustion control system based on Internet of Things (IoT) feedback control, characterized in that, The combustion control system includes: The first acquisition module is used to acquire basic information of a preset heating surface, wherein the basic information of the preset heating surface includes heating area information, boiler capacity information and heating cycle information. The intelligent matching module is used to match the desired heat exchange based on the heated area information, the boiler capacity information, and the heating cycle information. The intelligent upload module is used to upload flue gas temperature record data, wall temperature record data, and steam and water heating record data of a preset time granularity for the preset heated surface, based on the heat-resistant temperature sensor. The intelligent calculation module is used to calculate the first fouling coefficient based on the smoke temperature recording data, the wall temperature recording data, and the steam and water heating recording data; The second acquisition module is used to acquire combustion control parameters; The intelligent generation module is used to optimize the combustion control parameters based on the first fouling coefficient and the expected heat exchange, and generate the combustion control parameter optimization result; An intelligent execution module is used to perform boiler combustion control based on the optimization results of the combustion control parameters. The intelligent calculation module is further used to calculate a first absorption-to-release ratio coefficient based on the smoke temperature recording data and the wall temperature recording data, and to calculate a second absorption-to-release ratio coefficient based on the wall temperature recording data and the soda heating recording data, and then to calculate the first contamination coefficient based on the first absorption-to-release ratio coefficient and the second absorption-to-release ratio coefficient.

Images