Real-time monitoring system for combustion state of decomposition rotational flow ammonia-doped pulverized coal burner based on infrared temperature measurement

Abstract

The invention relates to the technical field of a decomposition rotational flow ammonia-doped pulverized coal burner combustion state real-time monitoring system based on infrared temperature measurement, and adopts the core technical scheme that the decomposition rotational flow ammonia-doped pulverized coal burner combustion state real-time monitoring system comprises an optical detection module, a signal processing module, a data fusion module and a graded monitoring module, wherein the optical detection module synchronously collects infrared radiation and ultraviolet chemiluminescence signals of combustion flames through an optical lens and a spectroscope, and the signal processing module processes a multiband infrared image and a free radical luminescence image to obtain a two-dimensional temperature field and distribution parameters. The data fusion module extracts feature parameters and generates comprehensive feature vectors, and the hierarchical monitoring module outputs qualitative state labels and quantitative risk scores based on an analysis model. According to the scheme, the problems that in the prior art, due to dependence on a single monitoring parameter, diagnosis of the ammonia-doped combustion state is not comprehensive, and the risk of ammonia escape or flameout cannot be early warned are solved, and the beneficial effects that the monitoring accuracy is improved, multi-parameter intelligent fusion diagnosis is achieved, and the combustion efficiency is optimized through active early warning are achieved.

Description

Technical Field

[0001] This invention relates to the field of infrared thermometry technology, specifically to a real-time monitoring system for the combustion status of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry. Background Technology

[0002] Ammonia-blended pulverized coal combustion technology has attracted widespread attention as an effective way to reduce carbon emissions. The introduction of ammonia can replace some fossil fuels and reduce carbon dioxide emissions, but it also significantly alters combustion characteristics. Existing combustion monitoring technologies mostly rely on traditional methods, such as acoustic methods or single optical means, but these methods have obvious limitations in dealing with the complexities of ammonia-blended combustion.

[0003] Chinese Patent No. CN116086614B discloses a method for monitoring the temperature field of a furnace cross section by combining radiation images and spectra. This method synchronously acquires flame radiation signals by using image detectors and spectrometers, and visualizes temperature distribution and radiation characteristic parameters by using reconstruction algorithms. Multiple image detectors are arranged in the observation holes of the furnace, and the flame radiation spectrum is obtained by combining them with a spectrometer, thereby correcting the emissivity ratio and improving the accuracy of temperature field reconstruction.

[0004] However, while the patent has the advantages of compact system and fast response in temperature monitoring of ordinary pulverized coal boilers, the infrared radiation images it relies on can only reflect temperature information through a limited band, with low spectral resolution. Furthermore, the reconstruction algorithm assumes that the radiation characteristics of the medium are uniform, which makes it difficult to adapt to the challenges brought by the non-uniform medium in ammonia-blended combustion. Although the collected flame radiation images and spectra can provide temperature field distribution, they lack the ability to diagnose key states such as combustion intensity and mixing uniformity. Summary of the Invention

[0005] The purpose of this invention is to provide a real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry. The system simultaneously acquires infrared radiation and ultraviolet chemiluminescence signals from the combustion flame via an optical detection module. A signal processing module analyzes the two-dimensional temperature field and the distribution characteristics of hydroxyl and amino free radicals. A data fusion module combines temperature and free radical information, extracts multiple characteristic parameters, and inputs them into an analysis model for intelligent diagnosis. Finally, a graded monitoring module outputs qualitative status labels ranging from "excellent" to "risk" and quantitative risk scores, enabling real-time assessment and early warning of combustion stability, mixing uniformity, and ammonia escape risk. This provides a reliable basis for burner optimization and adjustment, solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A real-time monitoring system for the combustion status of a decomposed swirl ammonia-blended pulverized coal burner based on infrared thermometry includes an optical detection module, a signal processing module, a data fusion module, and a graded monitoring module connected in sequence. The optical detection module includes an optical lens and a beam splitter. The optical lens is used to receive the broadband radiation signal of the burning flame. The beam splitter is located behind the optical lens and is configured to separate the incident beam into a beam that is transmitted to the infrared optical path component and a beam that is reflected to the ultraviolet optical path component. The infrared optical path is equipped with a multispectral infrared thermal imager, and a rotatable multispectral filter wheel is installed at its front end. The multispectral filter wheel is equipped with multiple narrowband filters with different center wavelengths. The ultraviolet optical path is equipped with an ultraviolet enhanced CCD camera, and a narrowband filter for detecting specific free radicals is installed at its front end. The signal processing module is configured to perform multispectral temperature field inversion processing on the infrared signal and free radical luminescence region analysis processing on the ultraviolet signal. The data fusion module is configured to extract temperature field characteristic parameters and free radical distribution characteristic parameters, and combine them into a comprehensive feature vector to input into the combustion state analysis model; The graded monitoring module is configured to output qualitative status labels and quantitative risk scores to provide graded early warning of combustion status.

[0007] Preferably, the signal processing module's processing of the infrared signal includes: Receive raw grayscale image data acquired by a multispectral infrared thermal imager, and convert the raw grayscale image data into a flame radiation intensity image; Based on the radiation intensity values ​​of multiple infrared bands, the true temperature and spectral emissivity of each pixel are calculated, a two-dimensional temperature field distribution is constructed, and the two-dimensional temperature field distribution is smoothed and filtered.

[0008] Preferably, the signal processing module's processing of the ultraviolet signal includes: The system receives chemiluminescence images acquired by an ultraviolet-enhanced CCD camera, performs background noise subtraction and smoothing on the chemiluminescence images, and generates hydroxyl radical luminescence regions and amino radical luminescence regions. Calculate the geometric centroid coordinates, total pixel intensity, distribution area, spatial overlap between the two regions, and Euclidean distance between the centroids of the hydroxyl radical luminescent region and the amino radical luminescent region.

[0009] Preferably, the feature parameter extraction process of the data fusion module includes: The signal processing module receives two-dimensional temperature field distribution data and free radical luminescence region data, and calculates the cross-sectional average temperature, maximum temperature, minimum temperature, temperature distribution standard deviation, temperature distribution uniformity index, reflux zone size, flame pulsation frequency, total intensity of hydroxyl radicals, total intensity of amino radicals, spatial overlap between the two regions, and centroid distance between the two regions. The characteristic parameters are combined into a comprehensive feature vector, which is then input into a pre-established combustion state analysis model.

[0010] Preferably, the process by which the graded monitoring module continuously monitors the combustion state includes: The system receives a comprehensive feature vector from the data fusion module and outputs a qualitative status label and a quantitative risk score based on the combustion status analysis model. The qualitative status labels include four levels: "Excellent", "Good", "Critical", and "Risk". The quantitative risk score is an integer level from 1 to 10, which is generated by weighted calculation of the deviation of characteristic parameters.

[0011] Preferably, the multispectral filter wheel is provided with three narrowband filters with center wavelengths of 3.8 micrometers, 4.1 micrometers and 4.2 micrometers, and the rotation of the filter wheel is matched with the camera exposure sequence.

[0012] Preferably, the narrowband filters equipped with the ultraviolet-enhanced CCD camera are used to detect hydroxyl radicals and amino radicals, respectively. The narrowband filter for detecting hydroxyl radicals has a center wavelength of approximately 309 nm and a bandwidth of 10 nm, while the narrowband filter for detecting amino radicals has a center wavelength of approximately 334 nm and a bandwidth of 10 nm.

[0013] Preferably, the signal processing module further includes the following steps for processing infrared signals: the processed two-dimensional temperature field distribution data is converted into a standard format, stored in a database, and simultaneously sent to the operation interface of the visualization module. The visualization module maps the data into a pseudo-color cloud map to display the temperature and uniformity of the combustion flame.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention constructs a monitoring system for synchronous acquisition and intelligent fusion of multimodal signals. By integrating infrared and ultraviolet optical paths through an optical detection module, the system can simultaneously acquire infrared radiation and ultraviolet chemiluminescence signals of combustion flames. A beam splitter separates the broadband radiation into two paths, which are received by a multispectral infrared thermal imager and an ultraviolet enhanced CCD camera, respectively, thereby achieving simultaneous capture of temperature field and free radical distribution. The dual signal source design solves the problem of incomplete monitoring caused by the reliance on a single signal in existing technologies.

[0015] 2. This invention uses a multispectral infrared thermal imager to switch between different bands via a filter wheel and calculates the true temperature and spectral emissivity of each pixel, effectively eliminating the influence of emissivity and improving the accuracy of the temperature field. The ultraviolet signal processing quantifies the ammonia mixing status by calculating parameters such as the centroid and overlap of the luminescent regions of hydroxyl and amino radicals. Flame radiation images and spectral data provide input for the processing. Its beneficial effect is that it significantly improves the accuracy of temperature field reconstruction and can evaluate the ammonia diffusion trajectory in real time, avoiding the risk of ammonia escape caused by poor mixing.

[0016] 3. This invention transforms diagnostic results into intuitive qualitative labels and quantitative scores, identifies slight abnormal trends through multi-parameter fusion, and provides early warnings when multiple parameters deviate from their optimal values, offering operators an adjustment window to prevent the combustion state from deteriorating. Attached Figure Description

[0017] Figure 1 This is a structural diagram of the combustion state real-time monitoring system module of the present invention; Figure 2 This is a flowchart of the real-time combustion state monitoring system of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] To address the shortcomings of existing technologies that rely on a single monitoring parameter, such as incomplete diagnosis of ammonia-blended combustion status and inability to provide early warnings of ammonia escape or flameout risks, please refer to [link to relevant documentation]. Figure 1-2 This embodiment provides the following technical solution: The real-time combustion status monitoring system for decomposition swirl ammonia-blended pulverized coal burners based on infrared thermometry mainly includes four functional modules: an optical detection module, a signal processing module, a data fusion module, and a graded monitoring module.

[0020] The system first synchronously acquires infrared and ultraviolet signals through an optical detection module. The specific settings and acquisition process are as follows: The optical detection module receives broadband radiation signals emitted by the burning flame through an optical lens. The broadband radiation signals include ultraviolet and infrared bands. A beam splitter is set behind the optical lens. The broadband radiation received by the optical lens is precisely separated into two paths by the beam splitter: one beam is transmitted and guided to the infrared light path, and the other beam is reflected and guided to the ultraviolet light path.

[0021] A multispectral infrared thermal imager is set up in the infrared optical path. A multispectral filter wheel is installed at the front end of the multispectral infrared thermal imager. The multispectral filter wheel is equipped with several narrowband filters with different center wavelengths to receive radiation intensity signals from multiple different infrared bands. Specifically, the bands of 3.8 micrometers, 4.1 micrometers, and 4.2 micrometers can be selected because they have a certain degree of penetration into smoke and are less affected by emissivity. The rotation of the filter wheel is precisely matched with the camera's exposure sequence, thereby acquiring radiation images of the same flame in different infrared bands within a very short time interval.

[0022] An ultraviolet-enhanced CCD camera is set up in the ultraviolet light path. The ultraviolet-enhanced CCD camera is also equipped with a narrowband filter. The core wavelength of the narrowband filter is precisely aligned with the chemiluminescence peak of the free radical to be measured, so as to accurately receive the luminescence signal of the free radical. Specifically, the center wavelength of the narrowband filter for detecting hydroxyl radicals is about 309 nm and the bandwidth is 10 nm, and the center wavelength of the narrowband filter for detecting amino radicals is about 334 nm and the bandwidth is 10 nm.

[0023] After the acquisition process, the system processes the infrared and ultraviolet signals through a signal processing module.

[0024] Specifically, the processing procedure for infrared signals is as follows: 1. Image Conversion: After the multispectral infrared thermal imager continuously captures the infrared radiation image of the flame at a high frame rate, it captures the original grayscale image data and converts it into a flame radiation intensity image that represents the radiation capability. At the same time, it calls the wavelength parameters corresponding to multiple pre-configured narrowband filters.

[0025] 2. Solving for the true temperature value: For each pixel in the observed flame radiation intensity image, the signal processing module synchronously reads the radiation intensity value corresponding to that pixel in all different infrared bands. The radiation intensity values ​​together constitute the unique radiation characteristics of that pixel. Subsequently, the system's built-in inversion program solves for the intrinsic relationship between radiation intensity and its true temperature and the spectral emissivity characteristics of the material itself based on these discrete radiation intensity data. The solution process calculates two values ​​simultaneously: one is the true temperature value of the flame region corresponding to that pixel, and the other is the spectral emissivity of the pixel in that band. This step is to effectively isolate the influence of spectral emissivity changes on the temperature measurement results, thereby obtaining a more accurate true temperature.

[0026] 3. Construction and post-processing of the temperature field: After solving for the true temperature value of each pixel in the image, the temperature data of all pixels are recombined into a complete temperature distribution field representing the two-dimensional field of view. This initial temperature distribution field is then smoothed and filtered to suppress abnormal temperature points that may be caused by random noise, thereby improving the reliability of the data.

[0027] 4. Storage and Display: The processed two-dimensional temperature field distribution data is converted into a standard format, stored in the database, and simultaneously sent to the operation interface of the visualization module. The visualization module maps it into a pseudo-color cloud map, intuitively displaying the temperature and uniformity of the combustion flame, providing the most direct temperature field distribution information for subsequent combustion state analysis.

[0028] Specifically, the processing procedure for ultraviolet signals is as follows: 1. Generating the luminescent region: The signal processing module simultaneously captures the chemiluminescence image of free radicals in the flame. First, the ultraviolet luminescence image is subjected to background noise reduction and smoothing to improve the signal-to-noise ratio. Then, by setting an appropriate intensity threshold, the effective hydroxyl radical luminescent region and amino radical luminescent region are segmented from the background.

[0029] 2. Calculate the geometric centroid coordinates, total pixel intensity, and distribution area of ​​the hydroxyl radical luminescent region and the amino radical luminescent region: The stability of the main combustion zone is determined by observing the stability of the geometric centroid coordinates of the hydroxyl radical luminescent region, while the geometric centroid coordinates of the amino radical luminescent region represent the mixing of the ammonia injection trajectory with the pulverized coal flame. The total pixel intensity represents the total amount of chemiluminescence in that region, used to indicate the reaction rate and reactant concentration. The total pixel intensity of hydroxyl radicals is a direct measure of overall combustion intensity, while the total pixel intensity of amino radicals reflects the abundance of unreacted ammonia in the local area. An abnormal increase or decrease in the distribution area may indicate a change in the combustion mode; for example, poor ammonia diffusion can lead to dispersion in the reaction area.

[0030] 3. Calculate the ratio of the overlapping area of ​​the hydroxyl radical luminescent region and the amino radical luminescent region to the total area: This ratio is the spatial overlap. If the spatial overlap is high, it means that the injected ammonia should mix quickly and evenly with the volatile matter of coal powder and air, and the combustion state is good. Conversely, it means that the ammonia is not mixed well with the main gas flow, or the local combustion conditions are deteriorated, the combustion state is poor, which means low fuel utilization efficiency.

[0031] 4. Calculate the Euclidean distance between the geometric centroid coordinates of the two luminescent regions: Under ideal conditions, the amino group is rapidly ignited and consumed, and its luminescent region should highly overlap with the luminescent region of the hydroxyl radical, with a very small centroid distance. If the centroid distance between the two distribution regions increases significantly or the overlap decreases sharply, it indicates that the mixing of ammonia, volatile matter in coal powder (volatile thermal decomposition products of organic matter in coal), and air has deteriorated, and there is a risk that ammonia may escape without participating in the reaction in time.

[0032] After signal processing, the system uses a data fusion module to further extract feature parameters from the infrared and ultraviolet signals. This is because the final state diagnosis of ammonia-blended pulverized coal combustion relies on the fusion analysis of these features, as detailed below: 1. Calculation parameters: The system calculates multiple characteristic parameters, including but not limited to the cross-sectional average temperature, maximum temperature, minimum temperature, temperature distribution standard deviation, temperature distribution uniformity index, reflux zone size, flame pulsation frequency, and the total intensity of hydroxyl radicals, total intensity of amino radicals, spatial overlap between the two zones, and centroid distance between the two zones provided by the infrared two-dimensional temperature distribution field data.

[0033] 2. Model Input: The above data are combined into a comprehensive feature vector, which is then input into a pre-established combustion state analysis model. This model can be based on rule thresholds or a machine learning model trained on a large amount of historical operating data. The model can learn the complex nonlinear mapping relationship between the feature vector and the combustion state under different operating conditions, thereby intelligently identifying the current state.

[0034] After the data fusion process, the system continuously monitors the combustion status through a hierarchical monitoring module. The model analyzes the input comprehensive feature vector to make a comprehensive diagnosis of the current combustion status and outputs qualitative status labels and quantitative risk scores, as follows: 1. Set qualitative labels: The qualitative status labels include four levels from excellent to poor: "Excellent", "Good", "Critical", and "Risk". The first level is "Excellent", which means that all parameters are within the ideal range, the flame temperature is high and evenly distributed, the free radical regions are highly overlapping, and the combustion is in the best state. The second level is "Good", which means that some parameters have begun to deviate from the optimal value, but the overall combustion is still stable. Staff need to pay attention, but no intervention is required. The third level is "Critical", which means that multiple parameters show obvious abnormalities at the same time, prompting operators to make adjustments. The fourth level is "Risk", which means that clear characteristics of near flameout or serious ammonia escape have been detected. The system issues the highest level alarm and performs protective operations manually or automatically.

[0035] 2. Setting Quantitative Scores: Each of the four qualitative status labels mentioned above is assigned a comprehensive quantitative risk score, providing a specific numerical scale for qualitative judgment. The score is set as an integer level from 1 to 10. The quantitative risk score is a weighted sum of the deviations of all characteristic parameters. Different parameters are assigned different weights according to their impact on combustion safety. Through weighted calculation, even if all parameters have not yet exceeded their respective warning thresholds, the simultaneous occurrence of small adverse trends in multiple parameters will lead to a slow and continuous increase in the comprehensive quantitative risk score. Real-time feedback of this change can help operators take early warning and prevention measures against risks, giving them sufficient time to analyze the causes and fine-tune operations, thereby preventing further deterioration of the combustion status.

[0036] Finally, the diagnostic results of the combustion status are displayed in real time on the operation interface and fed back to the operators, or used as a feedforward signal for the closed-loop control of the system. This provides a direct and reliable basis for the adaptive optimization and adjustment of the ammonia-blended pulverized coal burner, ultimately ensuring that the combustion of ammonia-blended pulverized coal continues to maintain an efficient and stable optimal state.

[0037] Working Principle: This invention is based on the collaborative operation of four functional modules: an optical detection module, a signal processing module, a data fusion module, and a hierarchical monitoring module. The system first acquires signals from the combustion flame through the optical detection module. This module uses an optical lens to receive the broadband radiation signal emitted by the flame, which includes both ultraviolet and infrared bands. A beam splitter separates the incident beam into two paths: the transmitted light is guided to the infrared path, and the reflected light is guided to the ultraviolet path, simultaneously acquiring infrared and ultraviolet data.

[0038] The acquired signals are then processed by the signal processing module. For infrared signals, a two-dimensional temperature field distribution is constructed. For ultraviolet signals, luminescent regions of hydroxyl radicals and amino radicals are generated. Then, the geometric centroid coordinates, total pixel intensity, distribution area, overlap ratio of the two regions, and Euclidean distance between the centroids of the luminescent regions are calculated.

[0039] The data fusion module extracts key feature parameters, combines them into a comprehensive feature vector, and inputs it into a pre-established combustion state analysis model to achieve intelligent identification. Finally, the graded monitoring module monitors the combustion state in real time based on the model output, outputting qualitative state labels and assigning quantitative risk scores. Early warning is achieved by calculating parameter deviations through weighted averages.

[0040] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0041] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

Claims

1. A real-time monitoring system for the combustion status of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, characterized in that, It includes an optical detection module, a signal processing module, a data fusion module, and a hierarchical monitoring module connected in sequence; The optical detection module includes an optical lens and a beam splitter. The optical lens is used to receive the broadband radiation signal of the burning flame. The beam splitter is located behind the optical lens and is configured to separate the incident beam into a beam that is transmitted to the infrared optical path component and a beam that is reflected to the ultraviolet optical path component. The infrared optical path is equipped with a multispectral infrared thermal imager, and a rotatable multispectral filter wheel is installed at its front end. The multispectral filter wheel is equipped with multiple narrowband filters with different center wavelengths. The ultraviolet optical path is equipped with an ultraviolet enhanced CCD camera, and a narrowband filter for detecting specific free radicals is installed at its front end. The signal processing module is configured to perform multispectral temperature field inversion processing on the infrared signal and free radical luminescence region analysis processing on the ultraviolet signal. The data fusion module is configured to extract temperature field characteristic parameters and free radical distribution characteristic parameters, and combine them into a comprehensive feature vector to input into the combustion state analysis model; The graded monitoring module is configured to output qualitative status labels and quantitative risk scores to provide graded early warning of combustion status.

2. The real-time combustion status monitoring system for a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry according to claim 1, characterized in that, The signal processing module's processing of infrared signals includes: Receive raw grayscale image data acquired by a multispectral infrared thermal imager, and convert the raw grayscale image data into a flame radiation intensity image; Based on the radiation intensity values ​​of multiple infrared bands, the true temperature and spectral emissivity of each pixel are calculated, a two-dimensional temperature field distribution is constructed, and the two-dimensional temperature field distribution is smoothed and filtered.

3. The real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry according to claim 1, characterized in that, The signal processing module's processing of ultraviolet signals includes: The system receives chemiluminescence images acquired by an ultraviolet-enhanced CCD camera, performs background noise subtraction and smoothing on the chemiluminescence images, and generates hydroxyl radical luminescence regions and amino radical luminescence regions. Calculate the geometric centroid coordinates, total pixel intensity, distribution area, spatial overlap between the two regions, and Euclidean distance between the centroids of the hydroxyl radical luminescent region and the amino radical luminescent region.

4. The real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry according to claim 1, characterized in that, The feature parameter extraction process of the data fusion module includes: The signal processing module receives two-dimensional temperature field distribution data and free radical luminescence region data, and calculates the cross-sectional average temperature, maximum temperature, minimum temperature, temperature distribution standard deviation, temperature distribution uniformity index, reflux zone size, flame pulsation frequency, total intensity of hydroxyl radicals, total intensity of amino radicals, spatial overlap between the two regions, and centroid distance between the two regions. The characteristic parameters are combined into a comprehensive feature vector, which is then input into a pre-established combustion state analysis model.

5. A real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, as described in claim 1, is characterized in that... The process by which the graded monitoring module continuously monitors the combustion state includes: The system receives a comprehensive feature vector from the data fusion module and outputs a qualitative status label based on the combustion state analysis model. The qualitative status label includes four levels: "excellent", "good", "critical" and "risk".

6. A real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, as described in claim 1, is characterized in that... The process of the graded monitoring module continuously monitoring the combustion state also includes: receiving a comprehensive feature vector from the data fusion module and outputting a quantitative risk score based on the combustion state analysis model; the quantitative risk score is an integer level from 1 to 10, which is generated by weighted calculation of the deviation of feature parameters.

7. A real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, as described in claim 1, is characterized in that... The multispectral filter wheel is equipped with narrowband filters with three center wavelengths of 3.8 micrometers, 4.1 micrometers, and 4.2 micrometers, and the rotation of the filter wheel is matched with the camera exposure sequence.

8. A real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, as described in claim 1, is characterized in that... The ultraviolet-enhanced CCD camera is equipped with narrowband filters for detecting hydroxyl radicals and amino radicals, respectively. The narrowband filter for detecting hydroxyl radicals has a center wavelength of approximately 309 nm and a bandwidth of 10 nm, while the narrowband filter for detecting amino radicals has a center wavelength of approximately 334 nm and a bandwidth of 10 nm.

9. A real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, as described in claim 1, is characterized in that... The signal processing module's processing of infrared signals also includes: the processed two-dimensional temperature field distribution data is converted into a standard format and sent to a database for storage.

10. A real-time monitoring system for the combustion state of a decomposition swirl ammonia-blended pulverized coal burner based on infrared thermometry, as described in claim 1, is characterized in that... The diagnostic results from the graded monitoring module are sent to the operation interface of the visualization module, which maps them into a pseudo-color cloud map to display the temperature and uniformity of the combustion flame.

Images