Boiler combustion control method and system based on data analysis

Abstract

The invention discloses a boiler combustion control method and system based on data analysis, and relates to the technical field of combustion intelligent management and control. The method comprises the steps that historical solid combustion data and historical gas combustion data are obtained; performing data analysis according to the historical solid combustion data to obtain a basic solid combustion control scheme; performing data analysis according to the historical gas combustion data to obtain a basic gas combustion control scheme; according to the basic solid combustion control scheme and the basic gas combustion control scheme, data analysis is conducted on the obtained task data of the current boiler, and a boiler basic combustion control scheme is obtained; and boiler combustion control is conducted according to the boiler basic combustion control scheme. According to the method, typical working conditions are divided by analyzing historical data, dynamic ratio adjustment of the solid and the gas fuel is completed, and the problems of insufficient adaptability and adjustment lag in the boiler combustion process are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent combustion management, and particularly relates to a boiler combustion control method and system based on data analysis. BACKGROUND

[0002] As a key heat supply equipment, the boiler is widely used in the fields of power, heating, chemical industry and civil heating. Its operation efficiency and combustion stability directly affect the energy utilization rate, equipment safety and environmental protection emission level.

[0003] At present, the boiler combustion process generally relies on manual experience or control strategies based on fixed parameters, which is difficult to adapt to complex working conditions such as fuel characteristic fluctuations and load changes. Especially in the mixed combustion or independent combustion scene of solid fuel and gas fuel, there is a lack of unified analysis and coordinated control of the characteristics of the two types of fuel. In terms of solid fuel, traditional methods mostly rely on temperature, pressure and other indirect parameters for adjustment, and the real-time sensing ability of key factors such as fuel mixing uniformity and particle distribution state is insufficient, which leads to lagging in proportion adjustment and easy to appear local coking or insufficient combustion. In terms of gas fuel, there is no systematic method for dynamic proportioning control of hydrogen and natural gas mixed gas, which is difficult to effectively control the emission of nitrogen oxides and other pollutants while ensuring the combustion efficiency. In addition, most control strategies do not fully consider the differentiated needs of fuel proportioning under different operating conditions, and lack of deep mining of historical data and fine division of typical working conditions, so that the control scheme has strong universality but weak pertinence, and it is difficult to realize the full-condition optimization of the combustion process.

[0004] Therefore, how to improve the efficiency and adaptability of the boiler combustion under different working conditions is a problem to be solved at present. SUMMARY

[0005] The main purpose of the present application is to provide a boiler combustion control method and system based on data analysis, which aims to solve the technical problem of how to improve the efficiency and adaptability of the boiler combustion under different working conditions.

[0006] To achieve the above-mentioned purpose, the present application provides a boiler combustion control method based on data analysis, which comprises: obtaining historical solid combustion data, historical gas combustion data and current task data of the boiler; performing data analysis on the historical solid combustion data to obtain a basic solid combustion control scheme; performing data analysis on the historical gas combustion data to obtain a basic gas combustion control scheme; performing data analysis on the preset current task data of the boiler according to the basic solid combustion control scheme and the basic gas combustion control scheme to obtain a basic boiler combustion control scheme; According to the boiler basic combustion control scheme, the boiler combustion control is performed, and the boiler basic combustion control scheme comprises each solid target height, each gas target height, a target biomass coal ratio required for combustion, and a target hydrogen gas ratio in a typical working condition.

[0007] In an embodiment, the step of performing data analysis according to the historical solid combustion data to obtain a basic solid combustion control scheme comprises: obtaining task data and solid state data of each historical combustion according to the historical solid combustion data; performing clustering analysis on the task data of each historical combustion according to a preset clustering algorithm to obtain task data of each type of typical working condition; calculating the similarity between the task data of each historical combustion and the task data of each type of typical working condition; taking the maximum value in the similarity as a typical working condition of each historical combustion; performing analysis according to the solid state data to obtain each solid target height in the typical working condition; setting a basic solid combustion control scheme according to each solid target height in the typical working condition.

[0008] In an embodiment, the solid state data comprises current mean value, current variance, and pulse frequency, and the step of performing analysis according to the solid state data to obtain each solid target height in the typical working condition comprises: performing variance calculation according to the current mean value, the current variance, and the pulse frequency to obtain current mean value variance, current variance value variance, and pulse frequency variance; performing weighted calculation after normalization of the current mean value variance, the current variance value variance, and the pulse frequency variance to obtain fluctuation indexes of each boiler height; sorting the fluctuation indexes of each boiler height according to a descending order to obtain a boiler height fluctuation sequence; taking a preset number of heights in the boiler height fluctuation sequence as solid risk heights to obtain each solid risk height in the typical working condition; determining each solid target height in the typical working condition according to each solid risk height in the typical working condition.

[0009] In an embodiment, the step of determining each solid target height in the typical working condition according to each solid risk height in the typical working condition comprises: summarizing each solid risk height in the typical working condition according to the type of the corresponding typical working condition to obtain a statistical number of each solid risk height; rank the solid risk heights under the typical working condition according to the statistical times to obtain a sequence of solid risk heights under the typical working condition; take the first preset number of heights in the sequence of solid risk heights as effective solid risk heights; determine a solid target height numerical interval according to the effective solid risk heights; screen each solid height under the typical working condition according to the solid target height numerical interval to obtain each solid target height.

[0010] In an embodiment, the step of setting a basic solid combustion control scheme according to each solid target height under the typical working condition comprises: obtain the current mean value, current variance, pulse number, combustion cost, burnout rate and heat release efficiency of each solid target height under the typical working condition; perform mean value calculation according to the current mean value, current variance and pulse number to obtain current mean value average, current variance average and pulse number average; perform normalization and weighting processing on the current mean value average, current variance average and pulse number average to obtain a combustion risk index under the typical working condition; perform normalization and weighting processing on the combustion risk index, combustion cost, burnout rate and heat release efficiency to obtain a combustion effect index under the typical working condition; determine a target biomass coal ratio under the typical working condition according to the combustion effect index, and set a basic solid combustion control scheme according to the target biomass coal ratio.

[0011] In an embodiment, the historical gas combustion data comprises hydroxyl methyl characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity and flame temperature, and the step of performing data analysis on the historical gas combustion data to obtain a basic gas combustion control scheme comprises: perform variance calculation on the hydroxyl methyl characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity and flame temperature to obtain hydroxyl methyl characteristic peak intensity ratio variance, nitrogen oxide characteristic peak intensity variance and flame temperature variance; perform normalization and weighting processing on the hydroxyl methyl characteristic peak intensity ratio variance, nitrogen oxide characteristic peak intensity variance and flame temperature variance to obtain a gas fluctuation index of each flame height; rank the gas fluctuation indices of each flame height to obtain a flame height fluctuation sequence; take the first preset number of flame heights in the flame height fluctuation sequence as gas risk heights; According to the gas risk height, a gas combustion risk index is obtained through analysis; Obtain the flame brightness uniformity, the furnace pressure fluctuation, and the air-fuel ratio deviation; According to the flame brightness uniformity, the furnace pressure fluctuation, and the air-fuel ratio deviation, normalization and weighting processing are performed to obtain a gas combustion effect index; According to the gas combustion effect index, a target hydrogen-natural gas ratio is determined, and a basic gas combustion control scheme is set according to the target hydrogen-natural gas ratio.

[0012] In an embodiment, the step of performing data analysis on the task data of the preset current boiler according to the basic solid combustion control scheme and the basic gas combustion control scheme to obtain a boiler basic combustion control scheme comprises: Perform cosine similarity calculation on the task data of the preset current boiler and the task data of various typical working conditions to obtain a typical working condition of the current boiler combustion; According to the typical working condition of the current boiler combustion, a corresponding biomass-coal ratio and a hydrogen-natural gas ratio are obtained from the basic solid combustion control scheme and the basic gas combustion control scheme; According to the biomass-coal ratio and the hydrogen-natural gas ratio, a boiler basic combustion control scheme is set.

[0013] In an embodiment, the step of performing boiler combustion control according to the boiler basic combustion control scheme comprises: Obtain boiler combustion state data under the boiler basic combustion control scheme, wherein the boiler combustion state data comprises a current mean value of the current boiler, a current variance, a pulse frequency, a hydroxyl-methine characteristic peak intensity ratio, a nitrogen oxide characteristic peak intensity, and a flame temperature; When the current mean value is less than a preset first target current mean value and the current variance is greater than a preset target current variance, the biomass-coal ratio is reduced; When the current mean value is greater than a preset second target current mean value and the pulse frequency is less than a preset first target pulse frequency, the biomass-coal ratio is increased; When the pulse frequency is less than a preset second target pulse frequency, the biomass-coal ratio is reduced, and a furnace soot-blowing device is started to simultaneously perform a pipeline coking early warning; When the hydroxyl-methine characteristic peak intensity ratio is less than a preset target intensity ratio and the flame temperature is less than a preset first target flame temperature, the hydrogen-natural gas ratio is increased; When the nitrogen oxide characteristic peak intensity is greater than a preset target characteristic peak intensity and the flame temperature is greater than a preset second target temperature, the hydrogen-natural gas ratio is reduced, and a flue gas recirculation device is started.

[0014] In an embodiment, the step of obtaining the boiler combustion state data under the boiler basic combustion control scheme comprises: collecting various solid combustion state data and various gas combustion state data under the boiler basic combustion control scheme; fitting the various solid combustion state data and the various gas combustion state data to obtain various solid combustion state slopes under each solid target height of the current boiler and various gas combustion state slopes of each flame target height; when the various solid combustion state slopes are in a preset solid combustion state slope interval, performing mean value calculation according to the various solid combustion state data to obtain the various solid combustion state data of the current boiler; when the various gas combustion state slopes are in a preset gas combustion state slope interval, performing mean value calculation according to the various gas combustion state data to obtain the various gas combustion state data of the current boiler; summarizing the various solid combustion state data and the various gas combustion state data to obtain the boiler combustion state data, wherein the boiler combustion state data comprises current mean value, current variance, pulse frequency, hydroxyl next methylene characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity and flame temperature of the current boiler.

[0015] In addition, to achieve the above object, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the steps of the above-mentioned boiler combustion control method based on data analysis.

[0016] In addition, to achieve the above object, the present application also provides a boiler combustion control system based on data analysis, which comprises a solid fuel data analysis module, a gas fuel analysis module and a boiler combustion data analysis module, and the boiler combustion control system based on data analysis is executed to realize the above-mentioned boiler combustion control method based on data analysis.

[0017] The application provides a boiler combustion control method based on data analysis, the method comprises the following steps: obtaining historical solid combustion data, historical gas combustion data and current boiler task data; performing data analysis on the historical solid combustion data to obtain a basic solid combustion control scheme; performing data analysis on the historical gas combustion data to obtain a basic gas combustion control scheme; performing data analysis on preset current boiler task data according to the basic solid combustion control scheme and the basic gas combustion control scheme to obtain a boiler basic combustion control scheme; and performing boiler combustion control according to the boiler basic combustion control scheme, wherein the boiler basic combustion control scheme comprises each solid target height, each gas target height, a target biomass coal ratio required for combustion and a target hydrogen gas ratio in a typical working condition. As can be seen, the application divides a typical working condition by analyzing historical data, screens a key risk height, determines an effective analysis area, completes dynamic proportioning adjustment of solid and gas fuels, solves the problems of insufficient adaptability and adjustment lag in the boiler combustion process, and improves the efficiency and adaptability of the boiler combustion under different working conditions. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings incorporated in and forming a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative labor.

[0020] Figure 1 A flowchart is provided for the first embodiment of the boiler combustion control method based on data analysis of the present application; Figure 2 A structure connection schematic diagram is provided for the boiler combustion control system based on data analysis of the present application; Figure 3 A flowchart is provided for the second embodiment of the boiler combustion control method based on data analysis of the present application; Figure 4 A flowchart is provided for the third embodiment of the boiler combustion control method based on data analysis of the present application.

[0021] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0023] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.

[0024] The main solution of the embodiment of the present application is: obtaining historical solid combustion data, historical gas combustion data and current boiler task data; performing data analysis according to the historical solid combustion data to obtain a basic solid combustion control scheme; performing data analysis according to the historical gas combustion data to obtain a basic gas combustion control scheme; performing data analysis on the preset current boiler task data according to the basic solid combustion control scheme and the basic gas combustion control scheme to obtain a boiler basic combustion control scheme; performing boiler combustion control according to the boiler basic combustion control scheme, and the boiler basic combustion control scheme includes each solid target height, each gas target height, a target biomass coal ratio required for combustion and a target hydrogen gas ratio under a typical working condition.

[0025] As a key heat supply equipment, the boiler has a wide application in the industrial fields of electric power, heating, chemical industry and civil heating. Its operation efficiency and combustion stability directly affect the energy utilization rate, equipment safety and environmental protection emission level.

[0026] At present, the boiler combustion process generally relies on manual experience or control strategies based on fixed parameters, which is difficult to adapt to complex working conditions such as fuel characteristic fluctuation and load change. Especially in the mixed combustion or independent combustion scene of solid fuel and gas fuel, there is a lack of unified analysis and coordinated control of the characteristics of the two types of fuel. In terms of solid fuel, traditional methods mostly rely on temperature, pressure and other indirect parameters for adjustment, and the real-time sensing ability of key factors such as fuel mixing uniformity and particle distribution state is insufficient, which leads to lagging adjustment of the ratio and easy occurrence of local coking or insufficient combustion. In terms of gas fuel, there is no systematic method for dynamic ratio control of mixed gas such as hydrogen and natural gas, which is difficult to effectively control the emission of nitrogen oxides and other pollutants while ensuring the combustion efficiency. In addition, most control strategies do not fully consider the differentiated needs of fuel ratio under different operating conditions, and lack of deep mining of historical data and fine division of typical working conditions, so that the control scheme has strong universality but weak pertinence, and it is difficult to realize the full-condition optimization of the combustion process. Therefore, how to improve the efficiency and adaptability of the boiler combustion under different conditions is a problem that needs to be solved at present.

[0027] It should be noted that the execution subject of the embodiment can be a boiler combustion control system based on data analysis, can be a computing service device with data processing, network communication and program running functions, or can be an electronic device capable of realizing the above-mentioned boiler combustion control function based on data analysis, and the embodiment is not specifically limited thereto. The following will take the boiler combustion control system based on data analysis as an example to describe the embodiment and the following embodiments.

[0028] Based on this, the embodiment of the present application provides a boiler combustion control method based on data analysis, referring to Figure 1 , Figure 1 is a flowchart of the first embodiment of the boiler combustion control method based on data analysis of the present application.

[0029] The boiler combustion control method based on data analysis is applied to a boiler combustion control system based on data analysis, and the system comprises a solid fuel data analysis module, a gas fuel analysis module and a boiler combustion data analysis module. Referring to Figure 2 , Figure 2 is a structural connection diagram of the boiler combustion control system based on data analysis of the present application.

[0030] In the embodiment, the boiler combustion control method based on data analysis comprises steps S10-S40: Step S10: obtaining historical solid combustion data and historical gas combustion data.

[0031] It should be noted that the historical solid combustion data includes task data and solid state data of each historical combustion, and the task data of each historical combustion includes but is not limited to steam flow, steam pressure and hot water flow of each historical combustion. In this step, the system will collect steam flow and hot water flow through the flow sensor, and collect steam pressure through the pressure sensor. The solid state data of each historical combustion includes the current mean, current variance and pulse frequency of each collected height of each boiler in each historical combustion. In addition, it should be noted that the current mean, variance, pulse frequency belong to process perception or combustion flow state feature data. It does not directly measure temperature or composition, but indirectly reflects the combustion state and potential problems by monitoring the dynamic behavior of the fuel particle flow in the combustion process. Specifically, the current mean refers to the average value of the high-speed collected current signal in a sampling time window (such as 1 second). It reflects the average electrical conductivity of the fuel mixture at that height section. The current variance refers to the dispersion degree of the current value relative to the mean value in the same time window. It reflects the uniformity and stability of the distribution of the fuel particle flow in time and space. When the fast-flowing, more conductive particles (such as metal impurities, high-carbon coke particles) or particle clusters pass through the electrode instantaneously, it will cause a transient spike (pulse) in the current, and the pulse frequency refers to the number of pulses per unit time, that is, the pulse frequency. It reflects the dynamic events of abnormal particle passing, particle agglomeration or flow obstruction (such as sudden release after slight blockage).

[0032] In addition, it should be noted that the historical gas combustion data is the gas state data of each historical combustion, and the gas state data of each historical combustion includes the hydroxyl methylene characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity and flame temperature of each flame height collected in each historical combustion. In this step, the system will identify the hydroxyl radical characteristic peak intensity and the methylene group characteristic peak intensity through the infrared spectrometer, divide the hydroxyl radical characteristic peak intensity by the methylene group characteristic peak intensity to obtain the hydroxyl methylene characteristic peak intensity ratio, identify the nitrogen oxide characteristic peak intensity through the spectrometer, and collect the flame temperature through the infrared spectrometer.

[0033] Step S20: performing data analysis according to the historical solid combustion data to obtain a basic solid combustion control scheme.

[0034] It should be noted that the basic solid combustion control scheme refers to inputting solid fuel based on the corresponding biomass-coal ratio of various typical working conditions. In this step, the system analyzes the historical solid combustion data, specifically including: clustering the task data of each historical combustion by clustering algorithm to obtain various typical working conditions (such as high load and high moisture, low load and low moisture, etc.); calculating the similarity of each historical combustion and each typical working condition by cosine similarity, and recording the typical working condition with the maximum similarity as the typical working condition of each historical combustion; analyzing the solid state data, calculating the fluctuation index of each boiler height, and sorting to obtain the solid risk height, and further summarizing to obtain the solid target height of each typical working condition; finally, based on the combustion state data of each solid target height, the combustion effect index is calculated, the optimal biomass-coal ratio is selected, and the basic solid combustion control scheme is formed. It can be understood that the role of this step is to mine typical working conditions and their corresponding optimal solid fuel ratio through historical data, and to provide preset optimization control strategies for different operating conditions.

[0035] Step S30: performing data analysis on the historical gas combustion data to obtain a basic gas combustion control scheme.

[0036] It should be noted that the basic gas combustion control scheme refers to inputting gas fuel based on the corresponding hydrogen-natural gas ratio of various typical working conditions. In this step, the system analyzes the historical gas combustion data, specifically including: calculating the gas fluctuation index of each flame height, sorting to obtain the gas risk height, and further summarizing to obtain the gas target height of each typical working condition; based on the gas state data of each gas target height, the gas combustion effect index is calculated, the optimal hydrogen-natural gas ratio is selected, and the basic gas combustion control scheme is formed. It can be understood that the role of this step is to establish an optimal matching scheme for gas fuel for typical working conditions, expand the application range of the system, and support intelligent control of solid-gas mixed combustion or pure gas fuel boilers.

[0037] Step S40: performing data analysis on the preset task data of the current boiler based on the basic solid combustion control scheme and the basic gas combustion control scheme to obtain a boiler basic combustion control scheme.

[0038] It should be noted that the current boiler task data (i.e. the current boiler usage data) refers to the data currently used by the system for the current boiler task arrangement, including steam flow, steam pressure and hot water flow. The boiler basic combustion control scheme refers to the input of solid fuel according to the current biomass-coal ratio of the boiler, and the input of gaseous fuel according to the current hydrogen-natural gas ratio of the boiler. In this step, the system analyzes the preset current boiler task data based on the basic solid combustion control scheme and the basic gaseous combustion control scheme, matches the typical working condition (working condition type) of the current boiler, obtains the corresponding biomass-coal ratio and hydrogen-natural gas ratio under the typical working condition (working condition type), and sets the boiler basic combustion control scheme based on the biomass-coal ratio and the hydrogen-natural gas ratio. The role of this step is to apply the historical data-driven optimization scheme to optimize the fuel ratio of the current boiler in real time, and to realize the self-adaptive basic combustion control of the working condition.

[0039] In a feasible implementation, the step S40 specifically comprises: Step S401: Perform cosine similarity calculation on the preset current boiler task data and the task data of various typical working conditions to obtain the typical working condition of the current boiler combustion.

[0040] It should be noted that in this step, the system performs cosine similarity calculation on the preset current boiler task data (such as steam flow, steam pressure and hot water flow) and the task data (such as steam flow average value, steam pressure average value and hot water flow average value under different types of typical working conditions) of various typical working conditions (i.e. several common working condition types) stored in the database, to obtain the similarity of the current boiler and various typical working conditions, and the typical working condition with the maximum similarity is recorded as the typical working condition of the current boiler combustion. It can be understood that the role of this step is to quickly and accurately identify the typical category to which the running state of the current boiler belongs based on historical data, and to provide a basis for subsequent ratio acquisition.

[0041] Step S402: According to the typical working condition of the current boiler combustion, the corresponding biomass-coal ratio and hydrogen-natural gas ratio are obtained from the basic solid combustion control scheme and the basic gaseous combustion control scheme.

[0042] It should be noted that in this step, the system will query the optimal biomass-coal ratio and hydrogen-natural gas ratio corresponding to the typical working condition from the basic solid combustion control scheme and the basic gaseous combustion control scheme stored in the system according to the typical working condition of the current boiler combustion. The basic solid combustion control scheme and the basic gaseous combustion control scheme are stored in the database in the form of a lookup table, and the key fields include typical working condition type, biomass-coal ratio and hydrogen-natural gas ratio.

[0043] Step S403: setting a boiler basic combustion control scheme according to the biomass-coal ratio and the hydrogen-gas ratio.

[0044] It should be noted that in this step, the system sets the acquired biomass-coal ratio and hydrogen-gas ratio as the basic combustion control scheme of the current boiler, i.e., controls the feeding device to input solid fuel according to the biomass-coal ratio and to input gaseous fuel according to the hydrogen-gas ratio.

[0045] Step S50: performing boiler combustion control according to the boiler basic combustion control scheme.

[0046] It should be noted that the boiler basic combustion control scheme includes each solid target height, each gaseous target height, a target biomass-coal ratio and a target hydrogen-gas ratio required for combustion under typical working conditions. In this step, the system performs combustion control according to the boiler basic combustion control scheme, which specifically includes: collecting, by a sensor, current boiler combustion state data (such as current mean current, current variance, pulse frequency, hydroxyl-methynol characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity and flame temperature) under each solid target height and each gaseous target height, and dynamically adjusting fuel ratio (target biomass-coal ratio and target hydrogen-gas ratio) or triggering a warning and auxiliary device based on the data. For example, if the mean current is less than a first target mean current and the current variance is greater than a target current variance, the biomass-coal ratio is reduced; if the pulse frequency is less than a second target pulse frequency, a coking warning is triggered and a soot-blowing device is started. It can be understood that the function of this step is to realize real-time monitoring and self-adaptive regulation of the combustion process, thereby improving combustion efficiency, stability and safety.

[0047] In addition, it should be noted that the dynamic adjustment adopts a fuzzy PID controller, which takes current mean current deviation and deviation change rate as input and dynamically outputs frequency converter speed adjustment amount of the feeder, thereby ensuring the accuracy and response speed of the adjustment.

[0048] In a feasible implementation, the step S50 specifically includes: Step S501: acquiring boiler combustion state data under the boiler basic combustion control scheme, the boiler combustion state data including current mean current, current variance, pulse frequency, hydroxyl-methynol characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity and flame temperature of the current boiler.

[0049] It should be noted that in this step, the system will collect various types of solid combustion state data (such as current mean, current variance, pulse frequency) at each solid target height under the boiler basic combustion control scheme in real time through the sensor network deployed in the boiler.

[0050] In addition, it should be noted that the sensor network includes but is not limited to: a double electrode detection device and a matching current sensor arranged at each height inside the boiler for collecting the current signal of the solid fuel; specifically, the double electrode detection device is arranged at each height inside the boiler, and a unit collection time window is preset, the current value of each record in the unit collection time window is collected by the current sensor, the current mean of each collection of each boiler height of each historical combustion is obtained by mean calculation, the current variance of each collection of each boiler height of each historical combustion is obtained by variance calculation, when a record current value is greater than a preset current value, it is recorded as a pulse, the pulse frequency of the unit collection time window is obtained by counting the pulse frequency of the unit collection time window, and the pulse frequency of each collection of each boiler height of each historical combustion is obtained.

[0051] In addition, it should be noted that the electrode plate is made of 316L stainless steel, and the electrode plate surface is coated with a ceramic anti-coking coating of aluminum oxide, and the current sensor is integrated with a PT100 temperature compensation module for correcting the current signal deviation caused by temperature drift.

[0052] Step S502: When the current mean is less than a preset first target current mean and the current variance is greater than a preset target current variance, the biomass coal ratio is reduced.

[0053] It should be noted that when it is monitored that the current mean of the current boiler is lower than the preset first target current mean, and the current variance exceeds the preset target current variance, it is determined that the biomass ratio in the current solid fuel is too high, which causes the overall conductivity to decrease and the mixing uniformity to deteriorate. The system immediately issues an instruction to reduce the proportion of biomass in the solid fuel by a preset proportion, and inputs the solid fuel accordingly.

[0054] In addition, it should be noted that the preset first target current mean is a key threshold for judging whether the current fuel mixing ratio is biased towards a too high biomass ratio, and the current mean is less than the preset first target current mean, which usually means that the biomass ratio is too high, because the conductivity of biomass is weaker than that of coal, which will cause the overall current mean to decrease. The target current variance refers to the current variance reference value of the corresponding height of the boiler under the current boiler operating condition when the solid fuel is mixed uniformly without local accumulation or segregation, i.e. the mixed uniformity standard value.

[0055] Step S503: When the current average current is greater than the preset second target average current and the pulse frequency is less than the preset first target pulse frequency, increase the biomass-to-coal ratio.

[0056] It should be noted that when the current average current of the boiler is higher than the second target average current and the pulse frequency is lower than the first target pulse frequency, it is determined that the proportion of coal in the current solid fuel is too high, resulting in enhanced electrical conductivity but insufficient particle flowability. The system then issues an instruction to increase the proportion of biomass in the solid fuel by a preset ratio. It should be understood that the purpose of this step is to improve the particle flow characteristics by increasing the biomass while ensuring that the electrical conductivity is not too high, thereby preventing local accumulation or insufficient combustion that may be caused by a high proportion of coal.

[0057] Additionally, it should be noted that the preset second target average current refers to the critical value of the average current of the boiler at the corresponding height when the proportion of coal in the solid fuel mixture is too high but has not yet reached the deterioration level of combustion under the current boiler operating conditions. It is the key reference for determining whether the proportion of coal is too high, and its value is higher than the preset first target average current. The preset first target pulse frequency refers to the reference value of the pulse frequency per unit time of the boiler at the corresponding height when the solid fuel particles flow smoothly without the risk of accumulation or blockage under the current boiler operating conditions.

[0058] Step S504: When the pulse frequency is less than the preset second target pulse frequency, reduce the biomass-to-coal ratio and start the furnace sootblowing device while warning of pipe coking.

[0059] It should be noted that when the pulse frequency of the current boiler is lower than the preset second target pulse frequency, it is determined that the flow of solid fuel particles has been significantly hindered, and there is a high risk of pipe coking or severe accumulation. The system will immediately perform three linked operations: reduce the biomass-to-coal ratio by a preset ratio to change the fuel characteristics; start the furnace sootblowing device for decoking intervention; and simultaneously trigger a pipe coking warning signal to notify the operator. It should be understood that the purpose of this step is to early warn and actively deal with the coking risk through the sensitive indicator of pulse frequency, to ensure the safety of boiler operation and prevent efficiency decline or equipment damage caused by blockage.

[0060] Additionally, it should be noted that the preset second target pulse frequency refers to the risk critical value of the pulse frequency per unit time of the boiler at the corresponding height when the flow of solid fuel particles has shown signs of significant obstruction under the current boiler operating conditions. It is the core reference for determining whether the risk of pipe coking or particle accumulation has reached the warning level, and its value is higher than the preset first target pulse frequency.

[0061] Step S505: When the intensity ratio of the hydroxyl methylene characteristic peak is less than the preset target intensity ratio and the flame temperature is less than the preset first target flame temperature, increase the ratio of hydrogen to natural gas.

[0062] It should be noted that in this step, when the intensity ratio of the hydroxyl methylene characteristic peak of the current boiler is lower than the preset target intensity ratio, and the flame temperature is lower than the preset first target flame temperature, it is determined that the gas fuel combustion is insufficient, and there is unburned hydrocarbon and insufficient heat release. The system then issues an instruction to increase the ratio of hydrogen in the gas fuel by a preset proportion. It can be understood that the purpose of this step is to optimize the gas fuel composition, improve the combustion sufficiency and the flame temperature, thereby improving the thermal efficiency and reducing the unburned pollutants, through the comprehensive judgment of spectral characteristics and temperature.

[0063] In addition, it should be noted that the preset target intensity ratio refers to the optimal intensity ratio of the hydroxyl radical characteristic peak to the methylene group characteristic peak when the gas fuel combustion is fully oxidized and there is no large amount of unburned hydrocarbon. The preset first target flame temperature is the lowest effective average temperature of the furnace flame when the gas fuel combustion is optimized in terms of heat release efficiency and there is no local low temperature leading to combustion deterioration under the current boiler gas combustion condition, which is a key threshold for determining whether the flame heat intensity meets the standard.

[0064] Step S506: When the intensity of the nitrogen oxide characteristic peak is greater than the preset target characteristic peak intensity and the flame temperature is greater than the preset second target temperature, reduce the ratio of hydrogen to natural gas, and start the flue gas recirculation device.

[0065] It should be noted that when the intensity of the nitrogen oxide characteristic peak of the current boiler is greater than the target characteristic peak intensity, and the flame temperature is higher than the second target temperature, it is determined that the combustion temperature is too high, resulting in excessive generation of nitrogen oxides. The system immediately performs two operations: reducing the ratio of hydrogen in the gas fuel by a preset proportion to suppress the flame temperature; and starting the flue gas recirculation device to introduce part of the low-temperature flue gas to reduce the temperature in the combustion zone. It can be understood that the purpose of this step is to synergistically control the fuel ratio and auxiliary systems to effectively suppress the generation of high-temperature nitrogen oxides and ensure that the emissions meet environmental protection standards.

[0066] In addition, it should be noted that the preset target characteristic peak intensity refers to the maximum allowed spectral intensity when the nitrogen oxide emission concentration meets the environmental protection standard; and the preset second target temperature refers to a critical temperature threshold that can cause a sudden increase in nitrogen oxides, which is higher than the preset first target flame temperature.

[0067] In one possible implementation, the step S501 specifically includes: Step A10: Collecting various types of solid combustion state data and various types of gas combustion state data under the boiler basic combustion control scheme.

[0068] It should be noted that in this step, the system will collect various types of solid combustion state data (such as average current, current variance, pulse frequency) at each solid target height and various types of gas combustion state data (such as hydroxyl methylene characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity, flame temperature) at each flame target height according to the solid target height and the gas target height corresponding to the typical working condition matched by the current boiler through the corresponding sensors.

[0069] In addition, it should be noted that the solid target height and the gas target height are the key monitoring regions with the most significant combustion state fluctuations and the most effective monitoring data under the typical working condition determined by historical data analysis in advance.

[0070] Step A20: Fitting the various types of solid combustion state data and the various types of gas combustion state data to obtain the various types of solid combustion state slopes at each solid target height and the various types of gas combustion state slopes at each flame target height of the current boiler.

[0071] It should be noted that in this step, the system will take the solid or flame target height of the boiler as the horizontal coordinate (the value from small to large), and the collected various types of state data as the vertical coordinate, fit the data points corresponding to each monitoring height into a curve (such as current mean-height curve, hydroxyl methylene characteristic peak intensity ratio-height curve), and calculate the slope of each type of solid combustion state data at each solid target height and the slope of each type of gas combustion state data at each flame target height through image recognition or numerical differentiation method. It can be understood that the role of this step is to convert the discrete height-data relationship into continuous slope characteristics to determine whether the change trend of the data in the spatial distribution is reasonable.

[0072] Step A30: When the various types of solid combustion state slopes are within the preset solid combustion state slope interval, performing mean value calculation according to the various types of solid combustion state data to obtain the various types of solid combustion state data of the current boiler.

[0073] It should be noted that for each solid target height, it is judged whether the calculated solid combustion state data slopes of each type (such as current mean slope, current variance slope, pulse number slope) fall within the preset corresponding solid combustion state slope interval. If all the slopes of a certain height meet the conditions, it is determined that the height is an effective particle analysis height. Then, the same type of solid combustion state data collected at all effective particle analysis heights is arithmetically averaged to finally obtain representative current boiler solid combustion state data of each type (such as current boiler current mean, current variance, and pulse number) for global analysis. It can be understood that the role of this step is to filter out the monitoring height with normal data trend and effectiveness through slope interval verification, exclude the interference of abnormal fluctuation region, and integrate the information of the key region through mean calculation, thereby improving the accuracy and robustness of state evaluation.

[0074] Step A40: When the gas combustion state slopes of each type are in the preset gas combustion state slope interval, the mean calculation is performed according to the gas combustion state data of each type to obtain the gas combustion state data of each type of the current boiler.

[0075] It should be noted that the principle is the same as that of step A30. For each flame target height, it is judged whether the calculated gas combustion state data slopes of each type (such as hydroxyl methylene characteristic peak intensity ratio slope, nitrogen oxide characteristic peak intensity slope, and flame temperature slope) fall within the preset corresponding gas combustion state slope interval. If all the slopes of a certain height meet the conditions, it is determined that the height is an effective gas analysis height. Then, the same type of gas combustion state data collected at all effective gas analysis heights is arithmetically averaged to finally obtain representative current boiler gas combustion state data of each type (such as current boiler hydroxyl methylene characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity, and flame temperature) for global analysis. It can be understood that the role of this step is to ensure that the data used for gas combustion control decision comes from the effective monitoring region with reasonable trend, thereby improving the accuracy of gas side control.

[0076] Step A50: The solid combustion state data of each type and the gas combustion state data of each type are summarized to obtain boiler combustion state data, and the boiler combustion state data includes current boiler current mean, current variance, pulse number, hydroxyl methylene characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity, and flame temperature.

[0077] It should be noted that in this step, the system integrates the obtained various types of solid combustion state data (current mean, current variance, pulse frequency) with various types of gas combustion state data (hydroxyl methylene characteristic peak intensity ratio, nitrogen oxide characteristic peak intensity, flame temperature) to form a complete set of current boiler combustion state data that has been verified for effectiveness and processed for mean value. The role of this step is to generate a unified, standardized and reliable set of real-time state parameters to provide direct basis for intelligent management and control logic.

[0078] The embodiment provides a boiler combustion control method based on data analysis. The method of the embodiment comprises the following steps: obtaining historical solid combustion data, historical gas combustion data and task data of a current boiler; performing data analysis on the historical solid combustion data to obtain a basic solid combustion control scheme; performing data analysis on the historical gas combustion data to obtain a basic gas combustion control scheme; performing data analysis on preset task data of the current boiler according to the basic solid combustion control scheme and the basic gas combustion control scheme to obtain a boiler basic combustion control scheme; and performing boiler combustion control according to the boiler basic combustion control scheme. The boiler basic combustion control scheme comprises a target height of each solid, a target height of each gas, a target biomass-coal ratio required for combustion and a target hydrogen-natural gas ratio in a typical working condition. As can be seen, the embodiment divides a typical working condition by analyzing historical data, screens a key risk height, and determines an effective analysis area (i.e., a height at which each type of solid combustion state data and each type of gas combustion state data should be collected before fuel ratio is adjusted), thereby completing dynamic adjustment of solid and gas fuels, solving the problems of insufficient adaptability and adjustment lag in the boiler combustion process, and improving the efficiency and adaptability of the boiler combustion under different working conditions.

[0079] Based on the first embodiment of the application, the same or similar contents as the above-mentioned first embodiment can be referred to the above description, and will not be described hereinafter. On this basis, please refer to Figure 3 , Figure 3 is a flowchart of the second embodiment of the boiler combustion control method based on data analysis of the application. The step S20 specifically comprises: Step S201: obtaining task data and solid state data of each historical combustion according to the historical solid combustion data.

[0080] It should be noted that the task data mainly comprises target operating parameters of the combustion, such as steam flow, steam pressure and hot water flow; and the solid state data comprises current mean, current variance and pulse frequency collected at different preset heights in the boiler during the combustion.

[0081] Step S202: performing clustering analysis on the task data of each historical combustion according to a preset clustering algorithm to obtain task data of each typical working condition.

[0082] It should be noted that in this step, the system will use a clustering algorithm (such as K-Means algorithm) to perform unsupervised clustering analysis on all historical combustion task data (steam flow, steam pressure, hot water flow). According to the characteristic similarity of these operating parameters, the historical combustion records are automatically divided into several clusters (Clusters), and each cluster represents a typical operating condition. Finally, the center or representative data of each cluster is extracted as the task data characteristics of this typical working condition. It can be understood that the role of this step is to automatically induce and refine limited and representative operating modes (i.e. typical working conditions) from massive historical operating data, to realize the standardized classification of complex operating states, and to provide a basis for subsequent precise matching and exclusive scheme formulation.

[0083] In addition, it should be noted that the typical working conditions can be divided into high-load high-moisture working conditions, low-load low-moisture working conditions, and high-load low-moisture working conditions, etc.

[0084] Step S203: calculating the similarity of the task data of each historical combustion and the task data of each typical working condition.

[0085] It should be noted that in this step, for each specific historical combustion record, the system will perform cosine similarity calculation on the feature vector formed by its task data and the task data feature vector of each typical working condition. Cosine similarity evaluates the similarity of two vectors by measuring the cosine value of the included angle between them in the direction. It can be understood that the role of this step is to quantify the matching degree of each historical combustion record with each preset typical working condition, and generate a similarity set, so as to objectively judge which kind of operating mode the historical combustion is closest to.

[0086] Step S204: taking the maximum value in the similarity as the typical working condition of each historical combustion.

[0087] It should be noted that in this step, for each historical combustion record, the maximum value is found by traversing the similarity calculated with all typical working conditions. The typical working condition corresponding to the maximum value is officially marked as the typical working condition to which this historical combustion belongs.

[0088] Step S205: analyzing the solid state data to obtain each solid target height under the typical working condition.

[0089] It should be noted that on the basis of having determined the attribution of each historical combustion record working condition, the system will conduct centralized analysis on the solid state data (i.e. the current mean value, current variance, pulse frequency at each boiler height) of all historical combustion records belonging to the same typical working condition. By calculating the fluctuation index of the state parameters at each height and sorting, the boiler height region with the most unstable combustion state and the highest risk under the typical working condition is identified, and these heights are determined as the solid target heights that need to be targeted for monitoring and management under the typical working condition.

[0090] Step S206: setting a basic solid combustion control scheme according to each solid target height under the typical working condition.

[0091] It should be noted that in this step, the system will conduct multi-objective comprehensive evaluation based on the historical solid state data collected at each solid target height corresponding to each typical working condition, as well as the economic and environmental indicators (such as combustion cost, burnout rate, heat release efficiency) under the working condition, and calculate the combustion effect index of each historical combustion. The biomass-to-coal ratio used in the historical record with the optimal combustion effect index under the typical working condition is selected to form a basic solid combustion control scheme for the working condition.

[0092] In a feasible implementation, the step S205 specifically comprises: Step B10: performing variance calculation according to the current mean value, the current variance and the pulse frequency to obtain the current mean value variance, the current variance value variance and the pulse frequency variance.

[0093] It should be noted that for each historical combustion record belonging to a certain typical working condition, the system will calculate the current mean value, current variance and pulse frequency at each boiler height, and the variance between different combustion periods (i.e. different historical records). Specifically, the variance of the current mean value (current mean value variance), the variance of the current variance (current variance value variance) and the variance of the pulse frequency (pulse frequency variance) of all historical records at each height are calculated. It can be understood that the purpose of this step is to quantify the dispersion degree and volatility of the key state parameters at each height in the historical operation from a statistical point of view, and to identify those unstable heights with large parameter value changes between different combustion periods.

[0094] Step B20: normalizing and weighted calculating the current mean value variance, the current variance value variance and the pulse frequency variance to obtain the fluctuation index of each boiler height.

[0095] It should be noted that in this step, the system will normalize the three variance values (current mean variance, current variance variance, and pulse frequency variance) of each boiler height calculated in the previous step by dividing them by the corresponding preset threshold values (such as current mean variance threshold, current variance variance threshold, and pulse frequency variance threshold), respectively, to eliminate the dimension effect and make the numerical values within a comparable range. Subsequently, the normalized three values are multiplied by the preset weight factors (such as current mean variance weight factor, current variance variance weight factor, and pulse frequency variance weight factor), respectively, and the weighted results are added together, to finally obtain the fluctuation index of each boiler height. It can be understood that the purpose of this step is to integrate the fluctuation information of three different dimensions to form a quantitative index that can comprehensively reflect the overall instability of each boiler height in history.

[0096] Additionally, it should be noted that the current mean variance threshold is used to distinguish whether the fluctuation of the current mean value at the same boiler height in different historical combustion periods is normal. When the current mean variance of a certain historical combustion period at this height is less than the threshold value, it indicates that the average current fluctuation at this height in different combustion periods is small, and the consistency of the fuel mixing ratio is good. If it is greater than the threshold value, it indicates that the average current fluctuation in different combustion periods is too large, which is caused by the abnormal stability of the feeding system. The current variance variance threshold is used to distinguish whether the fluctuation of the current variance at the same boiler height in different historical combustion periods is normal. The current variance reflects the uniformity of particle mixing in a single combustion, and its variance reflects the stability of the uniformity of mixing in different combustion periods. The pulse frequency variance threshold is used to distinguish whether the fluctuation of the pulse frequency at the same boiler height in different historical combustion periods is normal. The pulse frequency reflects the rhythm of particle flow through the electrode, and its variance reflects the stability of particle flow in different combustion periods.

[0097] Step B30: Sort the fluctuation indices of the respective boiler heights in descending order according to the order from large to small, to obtain a boiler height fluctuation sequence.

[0098] It should be noted that in this step, the system will arrange the fluctuation indices of the respective boiler heights in descending order according to the values of the fluctuation indices calculated, to generate an ordered list, i.e., a boiler height fluctuation sequence.

[0099] Step B40: Take the first preset number of heights in the boiler height fluctuation sequence as the solid risk heights, to obtain the respective solid risk heights under the typical working condition.

[0100] It should be noted that in this step, the system will select the top pre-set number of heights from the generated boiler height fluctuation sequence. These heights are formally marked as solid risk heights under the typical working condition. It can be understood that the role of this step is to objectively identify and lock the highest potential risk and most likely to appear abnormal combustion state under the typical working condition based on historical data.

[0101] Step B50: determining each solid target height under the typical working condition according to each solid risk height under the typical working condition.

[0102] It should be noted that in this step, the system will summarize the height information marked as solid risk in all historical combustion records under the typical working condition. By counting the frequency of these heights and performing sorting analysis, a representative solid target height numerical interval is finally determined. Among all the actual monitoring heights, the points falling within this numerical interval are determined as the solid target heights under the typical working condition. It can be understood that the role of this step is to data fuse and refine the risk heights identified in multiple historical combustions, find out the recognized and most critical height range that needs to be monitored in real-time operation, and form a stable and unified core monitoring target height set under the working condition.

[0103] In a feasible implementation, the step B50 specifically includes: Step B501: aggregating each solid risk height under the typical working condition according to the type of the corresponding typical working condition to obtain the statistical number of each solid risk height.

[0104] It should be noted that in this step, for each type of typical working condition (such as high load high moisture, low load low moisture, etc.), the system will aggregate the solid risk heights of each historical combustion belonging to the working condition and count the number of each height value. The role of this step is to identify which heights frequently appear risks under a specific typical working condition, thereby revealing the distribution rule of risk heights, providing a data basis for subsequent sorting and screening, and ensuring that the subsequent analysis focuses on the high-frequency risk area.

[0105] Step B502: sorting each solid risk height under the typical working condition according to the statistical number to obtain a boiler solid risk height sequence under the typical working condition.

[0106] It should be noted that in this step, for each type of typical working condition, the system will sort each solid risk height according to the statistical number from high to low to form a boiler solid risk height sequence of the working condition. The role of this step is to focus on those heights with the highest risk frequency in historical data, thereby realizing the focus on the key risk area, reducing the redundancy of data analysis, and improving the efficiency of subsequent processing.

[0107] Step B503: Take the first preset number of heights in the boiler solid risk height sequence as the effective solid risk heights.

[0108] It should be noted that in this step, the system selects the first N heights from the boiler solid risk height sequence as the effective solid risk heights, where N is a preset number, which is set by the staff according to the boiler structure, historical data volume, and risk tolerance.

[0109] Step B504: Determine the solid target height numerical interval according to the effective solid risk heights.

[0110] It should be noted that in this step, the system finds the maximum and minimum values in the effective solid risk heights, and then takes the maximum value as the upper limit of the solid target height numerical interval and the minimum value as the lower limit, thereby defining a continuous solid target height numerical interval. The solid target height numerical interval covers the range of all effective solid risk heights. This interval represents the region where risk heights concentrate under typical operating conditions, so target data collection and control need to be performed within this interval. The determination of the interval is based on historical data statistics, ensuring the comprehensiveness and representativeness of risk coverage.

[0111] Step B505: Screen each solid height under the typical operating conditions according to the solid target height numerical interval to obtain each solid target height.

[0112] It should be noted that for all boiler heights under the typical operating conditions, the system checks whether each height falls within the determined solid target height numerical interval. If so, the height is marked as a solid target height; otherwise, the height is excluded.

[0113] In one possible implementation, the step S206 specifically includes: Step C10: Obtain the current mean, current variance, pulse number, combustion cost, burnout rate, and heat release efficiency of each solid target height under the typical operating conditions.

[0114] It should be noted that in this step, the system will obtain the historical combustion data of each solid target height under the typical working condition from the database, including the current mean, current variance, pulse frequency, combustion cost, burnout rate and heat release efficiency. Among them, the combustion cost refers to the fuel cost consumed per unit time or per unit output. The burnout rate refers to the proportion of the combustible components in the fuel that are actually burned, which is usually obtained by analyzing the fixed carbon content in the ash. Then, the preset total carbon content is subtracted from the fixed carbon content in the ash, and then divided by the preset total carbon content to obtain the burnout rate. The preset total carbon content is obtained by the inherent properties of the fuel. The flue gas heat release loss rate is collected by the flue gas analyzer, and the flue gas heat release loss rate threshold is divided by the flue gas heat release loss rate to obtain the heat release efficiency.

[0115] Step C20: Calculate the average value of the current mean, the current variance and the pulse frequency to obtain the current mean average, the current variance average and the pulse frequency average.

[0116] It should be noted that in this step, the system will calculate the arithmetic mean of the current mean, the current variance and the pulse frequency of each solid target height to obtain the current mean average, the current variance average and the pulse frequency average under the typical working condition. For example, for the current mean of multiple solid target heights, the arithmetic mean is calculated as the current mean average.

[0117] Step C30: Normalize and weight the current mean average, the current variance average and the pulse frequency average to obtain the combustion risk index under the typical working condition.

[0118] It should be noted that in this step, the system will normalize the current mean average, the current variance average and the pulse frequency average to convert them to dimensionless values. The normalization method includes: taking the absolute value of the current mean average minus the current mean threshold, and then dividing by the current mean threshold to obtain the current mean normalization value; similarly process the current variance average and the pulse frequency average. Then, obtain the current mean weight factor, the current variance weight factor and the pulse frequency weight factor from the database, multiply the normalized values by the corresponding weight factors and sum them up to obtain the combustion risk index.

[0119] In addition, it should be noted that the current mean threshold refers to the safe boundary value of the current mean when the conductive properties of the mixed particles of the boiler solid fuel are stable, which is usually the lower limit of the current mean in the historical normal combustion data under this working condition. The weight factor is a proportionality coefficient set by the staff according to experience or experiment, which reflects the importance of each parameter to the combustion risk. The combustion risk index is a comprehensive index, and the higher the value, the greater the combustion risk, such as more serious problems of coking, uneven mixing, etc.

[0120] Step C40: normalizing and weighting the combustion risk index, the combustion cost, the burnout rate, and the heat release efficiency to obtain a combustion effect index under the typical working condition.

[0121] It should be noted that in this step, the system normalizes the combustion risk index, the combustion cost, the burnout rate, and the heat release efficiency. The normalization method includes: dividing the combustion risk index by the combustion risk index threshold to obtain a normalized value of the combustion risk index; dividing the combustion cost threshold by the combustion cost to obtain a normalized value of the combustion cost; dividing the burnout rate by the burnout rate threshold to obtain a normalized value of the burnout rate; and dividing the heat release efficiency by the heat release efficiency threshold to obtain a normalized value of the heat release efficiency. Then, the combustion risk index weight factor, the combustion cost weight factor, the burnout rate weight factor, and the heat release efficiency weight factor are obtained from the database, and the normalized values are multiplied by the corresponding weight factors and summed to obtain the combustion effect index. It can be understood that the purpose of this step is to evaluate the overall combustion effect under the typical working condition, balance the factors of risk, cost, efficiency, and environmental protection, and provide a comprehensive basis for optimizing the fuel ratio.

[0122] In addition, it should be noted that the combustion risk index threshold refers to the maximum acceptable value of the combustion risk index when the boiler combustion process is safe. The combustion cost threshold refers to the highest allowable cost value per unit of heat output when the boiler combustion reaches the industry economic operation standard. The burnout rate threshold refers to the minimum required value of the burnout rate when the fuel is fully combusted. The heat release efficiency threshold refers to the minimum required value of the heat release efficiency when the heat energy conversion reaches the design standard. The weight factor is set by the staff to adjust the contribution of each parameter to the combustion effect index.

[0123] Step C50: determining a target biomass-coal ratio under the typical working condition according to the combustion effect index, and setting a basic solid combustion control scheme according to the target biomass-coal ratio.

[0124] It should be noted that in this step, the system obtains the biomass-coal ratio and the corresponding combustion effect index of each historical collection under the typical working condition from the database. Then, the biomass-coal ratio corresponding to the collection with the highest combustion effect index is selected as the target biomass-coal ratio. Finally, the basic solid combustion control scheme is set as: under the typical working condition, the solid fuel is input according to the target biomass-coal ratio. It can be understood that the purpose of this step is to optimize the fuel ratio for each typical working condition to improve the combustion efficiency, reduce the risk and cost, and form a reusable benchmark scheme.

[0125] In addition, it should be noted that the target biomass-coal ratio refers to the mass ratio or volume ratio of biomass to coal that maximizes the combustion effect index.

[0126] In the embodiment, the typical working conditions are determined through cluster analysis and similarity matching, the key heights are screened in combination with the fluctuation indexes of solid state data, and the fuel ratio is optimized based on multi-parameter weighted calculation, so that the precise control of solid combustion is realized, the problems of low combustion efficiency, high risk and insufficient real-time in the prior art are solved, and the stability, safety and economy of boiler combustion are improved.

[0127] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as the above embodiments one and two can be referred to the above introduction, and will not be repeated hereinafter. On this basis, please refer to Figure 4 , Figure 4 is a flowchart of the third embodiment of the present application, and the step S30 specifically comprises: Step S301: According to the hydroxyl methylene characteristic peak intensity ratio, the nitrogen oxide characteristic peak intensity and the flame temperature, the variance calculation is performed to obtain the hydroxyl methylene characteristic peak intensity ratio variance, the nitrogen oxide characteristic peak intensity variance and the flame temperature variance.

[0128] It should be noted that in this step, the system will obtain the gas state data of each historical combustion from the database, specifically including the hydroxyl methylene characteristic peak intensity ratio, the nitrogen oxide characteristic peak intensity and the flame temperature collected multiple times under each flame height. For each flame height, the variances of the above three parameters in different historical combustion periods are calculated respectively: the hydroxyl methylene characteristic peak intensity ratio variance, the nitrogen oxide characteristic peak intensity variance and the flame temperature variance. It can be understood that the role of this step is to quantify the fluctuation degree of the key gas combustion state parameters of each flame height in different combustion periods, and to identify the unstable combustion height region, so as to provide a data basis for subsequent risk height screening.

[0129] Step S302: According to the hydroxyl methylene characteristic peak intensity ratio variance, the nitrogen oxide characteristic peak intensity variance and the flame temperature variance, the normalization and weighting processing are performed to obtain the gas fluctuation index of each flame height.

[0130] It should be noted that in this step, the system will normalize the variance of the hydroxyl methylene characteristic peak intensity ratio, the variance of the nitrogen oxide characteristic peak intensity and the variance of the flame temperature of each flame height by dividing them by their corresponding preset threshold values (hydroxyl methylene characteristic peak intensity ratio variance threshold value, nitrogen oxide characteristic peak intensity variance threshold value, and flame temperature variance threshold value), respectively. Then, the weight factors (hydroxyl methylene characteristic peak intensity ratio variance weight factor, nitrogen oxide characteristic peak intensity variance weight factor, and flame temperature variance weight factor) of each parameter are obtained from the database, and the normalized values are multiplied by the corresponding weight factors and summed to obtain the gas fluctuation index of each flame height. It can be understood that the purpose of this step is to integrate variance values of different dimensions and ranges into a comprehensive gas fluctuation index, which facilitates subsequent unified evaluation and ranking of risks at different flame heights.

[0131] Step S303: Sort the gas fluctuation indexes of each flame height to obtain a flame height fluctuation sequence.

[0132] It should be noted that in this step, the system will arrange all the gas fluctuation indexes of the flame heights in descending order according to the numerical values to form a flame height fluctuation sequence.

[0133] Step S304: Select the first preset number of flame heights in the flame height fluctuation sequence as the gas risk heights.

[0134] It should be noted that in this step, the system will select the first M flame heights from the flame height fluctuation sequence as the gas risk heights, where M is a preset number set by the staff according to the boiler structure, historical data analysis results and risk control requirements. It can be understood that the purpose of this step is to select the most representative gas risk heights to avoid wasting resources by equally analyzing all heights, thereby achieving accurate and efficient risk positioning.

[0135] Step S305: Analyze the gas risk heights to obtain a gas combustion risk index.

[0136] It should be noted that in this step, the system will collect the gas risk height based on the typical working conditions of each historical combustion (obtained by task data clustering and cosine similarity matching), and statistically analyze the gas risk height by type of typical working condition to determine the gas target height under each type of typical working condition (the specific determination process can refer to the determination method of the solid target height in the solid fuel, such as summarizing the number of statistics, sorting, determining the numerical interval, screening, etc.). Then, the historical data of the hydroxyl methylene characteristic peak intensity ratio, the nitrogen oxide characteristic peak intensity and the flame temperature of each gas target height under each type of typical working condition are obtained, and the average value is calculated. Next, the average value is normalized (for example, compared with the respective threshold value and the relative difference value is calculated) and weighted, and finally the gas combustion risk index of each type of typical working condition is obtained. It can be understood that the role of this step is to quantify the comprehensive combustion risk in the key gas target height region under a specific typical working condition, and to provide a risk dimension input for subsequent optimization of the gas fuel ratio.

[0137] In addition, it should be noted that the gas combustion risk index is a comprehensive index for a specific typical working condition, which reflects the potential risk size caused by insufficient combustion, excessive emission or abnormal temperature in the key gas target height region under this working condition.

[0138] Step S306: Obtain the flame brightness uniformity, the furnace pressure fluctuation and the air-fuel ratio deviation.

[0139] It should be noted that in this step, the system will obtain the flame brightness uniformity, the furnace pressure fluctuation and the air-fuel ratio deviation data collected in each historical combustion under each type of typical working condition from the database. These data are obtained through corresponding sensors and algorithms: the flame brightness uniformity is obtained by capturing the flame image through an industrial camera and quantifying it through an image analysis algorithm; the furnace pressure fluctuation is obtained by calculating the pressure range in a single combustion period after continuously collecting the furnace pressure through a pressure sensor; and the air-fuel ratio deviation is obtained by comparing the actual air-fuel ratio calculated by the air and fuel flow collected by the flow sensor with the theoretical air-fuel ratio. It can be understood that the role of this step is to collect other key parameters that affect the gas combustion effect and stability, and to prepare for a comprehensive evaluation of the combustion effect.

[0140] In addition, it should be noted that the flame brightness uniformity reflects the uniformity of the flame distribution in the furnace, and the higher the value, the more stable the combustion; the furnace pressure fluctuation reflects the stability of the furnace pressure, and the smaller the value, the more stable the operation; and the air-fuel ratio deviation reflects the deviation of the actual air-fuel ratio from the theoretical optimal value, and the smaller the value, the better the fuel and air mixing ratio.

[0141] Step S307: Normalize and weight the flame brightness uniformity, the furnace pressure fluctuation and the air-fuel ratio deviation to obtain a gas combustion effect index.

[0142] It should be noted that in this step, the system will normalize the gas combustion risk index, flame brightness uniformity, furnace pressure fluctuation and air-fuel ratio deviation. Specifically: divide the gas combustion risk index threshold by the gas combustion risk index to obtain the gas combustion risk index normalization value (the larger the value, the smaller the risk); divide the flame brightness uniformity by the flame brightness uniformity threshold to obtain the flame brightness uniformity normalization value; divide the furnace pressure fluctuation threshold by the furnace pressure fluctuation to obtain the furnace pressure fluctuation normalization value; divide the air-fuel ratio deviation threshold by the air-fuel ratio deviation to obtain the air-fuel ratio deviation normalization value. Then, obtain the weight factors of each parameter (gas combustion risk index weight factor, flame brightness uniformity weight factor, furnace pressure fluctuation weight factor, air-fuel ratio deviation weight factor) from the database, multiply the normalized values by the corresponding weight factors, and sum to obtain the gas combustion effect index. It can be understood that the role of this step is to build a comprehensive evaluation index, balancing the consideration of combustion risk, flame stability, pressure stability and air-fuel ratio rationality, to find the historical gas combustion record with the best comprehensive performance.

[0143] In addition, it should be noted that the normalization and weighting processing logic of this step is similar to the calculation of the combustion effect index in solid fuel, aiming to integrate multiple dimensions into a comparable comprehensive index. The threshold values and weight factors of each parameter are set by the staff according to factors such as operation goals, safety standards and economic benefits. The higher the gas combustion effect index value, the better the comprehensive performance of the gas combustion record in terms of safety, stability, economy and environmental protection.

[0144] Step S308: Determine the target hydrogen-natural gas ratio according to the gas combustion effect index, and set the basic gas combustion control scheme according to the target hydrogen-natural gas ratio.

[0145] It should be noted that in this step, for each type of typical working condition, the system will find the historical acquisition record with the highest gas combustion effect index from the database, and determine the hydrogen-natural gas ratio corresponding to this record as the target hydrogen-natural gas ratio. Then, set the basic gas combustion control scheme as follows: under this type of typical working condition, input the gas fuel according to the target hydrogen-natural gas ratio. It can be understood that the role of this step is to match a verified hydrogen-natural gas ratio with the best comprehensive effect in history for each typical working condition, forming a benchmark control strategy, and providing a basis for efficient, safe and economic gas combustion.

[0146] In the embodiment, the key risk height is identified by analyzing the volatility of the gas combustion state parameters, and the fuel ratio is optimized by comprehensively considering the combustion stability, environmental protection and economic indicators, so as to realize the precise regulation and control of gas combustion, solve the problem of lack of dynamic optimization and real-time response of gas fuel in the traditional method, and improve the efficiency, safety and environmental protection of boiler combustion.

[0147] In addition, the application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the boiler combustion control method based on data analysis as described above.

[0148] The computer program product provided by the application can solve the technical problem of how to improve the efficiency and adaptability of boiler combustion under different working conditions. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the boiler combustion control method based on data analysis provided by the above-mentioned embodiments, and are not repeated here.

[0149] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0150] The above is only a specific implementation of the application, but the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the application, which should be covered within the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

[0151] The flowcharts and block diagrams in the drawings illustrate the possible implementation architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, program segment or a part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different order than that shown in the figure. For example, two blocks represented in succession can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the function involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0152] The modules described in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0153] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or the like, which is made based on the technical concept of the present application and the content of the specification and drawings, is included in the patent protection scope of the present application.

Claims

1. A boiler combustion control method based on data analysis, characterized in that, The method includes: Acquire historical solid combustion data and historical gas combustion data; Based on the historical solid combustion data, a basic solid combustion control scheme is obtained through data analysis. Based on the historical gas combustion data, a basic gas combustion control scheme is obtained through data analysis. Based on the basic solid combustion control scheme and the basic gas combustion control scheme, data analysis is performed on the preset task data of the current boiler to obtain the basic combustion control scheme of the boiler. Boiler combustion control is performed according to the boiler basic combustion control scheme, which includes the target heights of each solid and each gas under typical operating conditions, the target biomass-coal ratio required for combustion, and the target hydrogen-to-natural gas ratio.

2. The method as described in claim 1, characterized in that, The step of analyzing the historical solid combustion data to obtain a basic solid combustion control scheme includes: Based on the historical solid combustion data, task data and solid state data for each historical combustion event are obtained; The task data of each historical combustion are clustered and analyzed according to a preset clustering algorithm to obtain task data for various typical working conditions. Calculate the similarity between the historical combustion task data and the task data of various typical operating conditions; The maximum value among the similarities is taken as the typical operating condition of each historical combustion. Based on the analysis of the solid state data, the heights of each solid target under the typical working conditions are obtained. A basic solid combustion control scheme is set according to the target height of each solid under the typical operating conditions.

3. The method as described in claim 2, characterized in that, The solid state data includes the mean current, current variance, and pulse frequency. The step of analyzing the solid state data to obtain the height of each solid target under the typical operating condition includes: Variance is calculated based on the mean current, the variance of the current, and the pulse frequency to obtain the variance of the mean current, the variance of the current variance, and the variance of the pulse frequency. The mean variance of the current, the variance of the current variance value, and the variance of the pulse frequency are normalized and then weighted to obtain the fluctuation index of each boiler height. The fluctuation indices of each boiler height are sorted in descending order to obtain the boiler height fluctuation sequence; The heights of the first preset number in the boiler height fluctuation sequence are taken as solid risk heights to obtain the solid risk heights under the typical operating conditions. The target heights of each solid under the typical operating conditions are determined based on the risk heights of each solid under the typical operating conditions.

4. The method as described in claim 3, characterized in that, The step of determining the target height of each solid under the typical operating condition based on the risk height of each solid under the typical operating condition includes: The solid risk heights under the typical working conditions are summarized according to the corresponding types of the typical working conditions to obtain the statistical frequency of each solid risk height. The solid risk heights under the typical operating conditions are sorted according to the statistical frequency to obtain the boiler solid risk height sequence under the typical operating conditions. The height of the first preset number of heights in the boiler solid risk height sequence is taken as the effective solid risk height. The numerical range of the solid target height is determined based on the effective solid risk height. Based on the numerical range of the solid target height, the heights of each solid under the typical working condition are filtered to obtain the height of each solid target.

5. The method as described in claim 2, characterized in that, The steps for setting the basic solid combustion control scheme based on the target height of each solid under the typical operating conditions include: The mean current, variance of current, number of pulses, combustion cost, burnout rate and heat release efficiency of each solid target height under the typical working conditions are obtained. The average values ​​of the current mean, the current variance, and the pulse count are calculated to obtain the average current mean, the average current variance, and the average pulse count. The average current value, the average current variance, and the average number of pulses are normalized and weighted to obtain the combustion risk index under the typical operating condition. The combustion risk index, combustion cost, burnout rate and heat release efficiency are normalized and weighted to obtain the combustion effect index under the typical working condition. The target biomass-coal ratio under the typical operating conditions is determined based on the combustion effect index, and a basic solid combustion control scheme is set based on the target biomass-coal ratio.

6. The method as described in claim 1, characterized in that, The historical gas combustion data includes the intensity ratio of the characteristic peak of hydroxymethyl group, the characteristic peak intensity of nitrogen oxides, and the flame temperature. The step of analyzing the historical gas combustion data to obtain a basic gas combustion control scheme includes: The variances of the hydroxymethyl characteristic peak intensity ratio, the nitrogen oxide characteristic peak intensity, and the flame temperature are calculated to obtain the variances of the hydroxymethyl characteristic peak intensity ratio, the nitrogen oxide characteristic peak intensity, and the flame temperature. The gas fluctuation index for each flame height is obtained by normalizing and weighting the variance of the intensity ratio of the characteristic peak of hydroxymethyl, the variance of the intensity of the characteristic peak of nitrogen oxides, and the variance of the flame temperature. The gas fluctuation indices of each flame height are sorted to obtain the flame height fluctuation sequence; The first preset number of flame heights in the flame height fluctuation sequence are taken as the gas risk height; Based on the gas risk level analysis, a gas combustion risk index is obtained; To obtain flame brightness uniformity, furnace pressure fluctuation, and air-fuel ratio deviation; The gas combustion effect index is obtained by normalizing and weighting the flame brightness uniformity, the furnace pressure fluctuation, and the air-fuel ratio deviation. The target hydrogen-to-natural gas ratio is determined based on the gas combustion effect index, and a basic gas combustion control scheme is set based on the target hydrogen-to-natural gas ratio.

7. The method as described in claim 1, characterized in that, The step of performing data analysis on the current boiler task data based on the basic solid combustion control scheme and the basic gas combustion control scheme to obtain the boiler basic combustion control scheme includes: The cosine similarity is calculated by comparing the current boiler's task data with the task data of various typical operating conditions to obtain the typical operating conditions of the current boiler combustion. Based on the typical operating conditions of the current boiler combustion, the corresponding biomass-coal ratio and hydrogen-natural gas ratio are obtained from the basic solid combustion control scheme and the basic gas combustion control scheme. A basic combustion control scheme for the boiler is set according to the biomass-coal ratio and the hydrogen-natural gas ratio.

8. The method as described in claim 1, characterized in that, The steps for boiler combustion control based on the boiler basic combustion control scheme include: Obtain boiler combustion status data under the boiler basic combustion control scheme. The boiler combustion status data includes the current mean value, current variance, number of pulses, intensity ratio of hydroxymethyl characteristic peak, intensity of nitrogen oxide characteristic peak, and flame temperature of the current boiler. When the mean current is less than the preset first target mean current and the variance of the current is greater than the preset target variance of the current, the biomass-coal ratio is reduced. When the average current is greater than the preset second target average current and the number of pulses is less than the preset first target number of pulses, the biomass-coal ratio is increased; When the number of pulses is less than the preset second target number of pulses, the biomass coal ratio is reduced, and the furnace soot blowing device is activated while a pipeline coking warning is issued. When the intensity ratio of the characteristic peak of hydroxymethyl is less than the preset target intensity ratio and the flame temperature is less than the preset first target flame temperature, the hydrogen-to-natural gas ratio is increased. When the intensity of the nitrogen oxide characteristic peak is greater than the preset target characteristic peak intensity and the flame temperature is greater than the preset second target temperature, the hydrogen-to-natural gas ratio is reduced and the flue gas recirculation device is activated.

9. The method as described in claim 8, characterized in that, The steps for obtaining boiler combustion status data under the basic boiler combustion control scheme include: Collect various solid combustion state data and various gas combustion state data under the boiler basic combustion control scheme; By fitting the various solid combustion state data and various gas combustion state data, the slopes of various solid combustion states and various gas combustion states at various solid target heights of the current boiler are obtained; When the slope of each type of solid combustion state is within the preset solid combustion state slope range, the average value of each type of solid combustion state data is calculated to obtain the current solid combustion state data of the boiler. When the slope of the combustion state of each type of gas is within the preset gas combustion state slope range, the average value is calculated based on the combustion state data of each type of gas to obtain the current combustion state data of each type of gas in the boiler. The boiler combustion status data is obtained by summarizing the various solid combustion status data and the various gas combustion status data. The boiler combustion status data includes the current average value, current variance, number of pulses, intensity ratio of hydroxymethyl characteristic peak, intensity of nitrogen oxide characteristic peak, and flame temperature of the current boiler.

10. A boiler combustion control system based on data analysis, characterized in that, The data analysis-based boiler combustion control system includes: a solid fuel data analysis module, a gaseous fuel analysis module, and a boiler combustion data analysis module. When the data analysis-based boiler combustion control system is executed, it implements the steps of the data analysis-based boiler combustion control method as described in any one of claims 1 to 9.

Images