Early warning method and device for combustion state of opposed firing boiler and computer equipment

Abstract

The invention discloses an early warning method and device for the combustion state of an opposed firing boiler and computer equipment. Comprising the steps of obtaining multi-source temperature data in the opposed firing boiler and parameter characteristics of flues on the left side and the right side of the opposed firing boiler; determining wall surface heating characteristics based on the wall surface temperature distribution data; based on the temperature distribution data in the boiler, adopting a DBSCAN spatial clustering algorithm to cluster each target monitoring point in the opposed firing boiler, positioning a flame center of a flame area, and determining behavior characteristics of a flame center movement track based on attribute characteristics of the flame center in continuous time frames; and matching the behavior characteristics, the wall surface heating characteristics and the parameter characteristics of the flue on the left side and the right side of the opposed firing boiler with early warning conditions, and carrying out slagging, partial combustion or overtemperature early warning according to a matching result. A plurality of flame centers can be automatically identified, the misjudgment rate of the number of the flame centers is reduced, the problem of insufficient early warning accuracy can be solved, and the operation safety of the boiler is improved.

Description

Technical Field

[0001] This application relates to the field of thermal power generation and monitoring technology, and in particular to a method, device and computer equipment for early warning of the combustion status of a counter-fired boiler. Background Technology

[0002] In the field of thermal power generation, opposed-burner boilers are widely used due to their advantages of high combustion efficiency and low pollutant emissions. Opposed-burner boilers consist of multiple layers arranged on the front and rear walls of the furnace water-cooled walls. Pulverized coal gas is ejected from the burners on the front and rear walls, and the opposing combustion creates a predominantly upward airflow. The multi-flame opposing combustion characteristics of opposed-burner boilers determine that the number, location, and temperature distribution of flame centers directly affect the unit's combustion efficiency, load regulation accuracy, and pollutant emission levels.

[0003] In existing technologies, the focus is on a single flame center device, and its flame field exhibits the characteristics of a single core and concentrated high-temperature areas. However, the multi-flame counter-firing combustion of a counter-firing boiler may form multiple independent flame cores, and there is high-temperature flue gas interference between the flames. Existing clustering models do not consider the spatial competition and interference characteristics of multiple flame cores. When directly applied to counter-firing boilers, they are prone to misjudgment of "multi-flame merging identification" and cannot adapt to the operating conditions of optimizing and adjusting individual burners in counter-firing boilers. Summary of the Invention

[0004] In view of this, this application provides a method, device and computer equipment for early warning of the combustion state of a counter-fired boiler. Through scenario adaptation, algorithm dimension separation and weighted model optimization, it achieves a comprehensive improvement in flame center recognition accuracy, anti-interference ability and industrial adaptability.

[0005] According to a first aspect of this application, a method for early warning of the combustion state of a counter-firing boiler is provided, the method comprising:

[0006] Acquire multi-source temperature data and parameter characteristics of the left and right flues of the opposed combustion boiler, wherein the multi-source temperature data includes furnace temperature distribution data and wall temperature distribution data. The wall heating characteristics are determined based on the wall temperature distribution data. Based on the furnace temperature distribution data, the DBSCAN spatial clustering algorithm is used to cluster each target monitoring point in the counter-fired boiler, locate the flame center of the flame area, and determine the behavioral characteristics of the flame center's motion trajectory based on the attribute characteristics of the flame center in continuous time frames. The behavioral characteristics, wall heating characteristics, and parameter characteristics of the left and right flues of the opposed combustion boiler are matched with the early warning conditions, and early warnings for slagging, uneven burning, or overheating are issued based on the matching results.

[0007] Optionally, the step of clustering the target monitoring points in the opposed-fired boiler using the DBSCAN spatial clustering algorithm based on the furnace temperature distribution data to locate the flame center of the flame region includes: Acquire three-dimensional time-series data of the flame region inside the counter-fired boiler, and filter out the target monitoring points whose temperature is higher than a first temperature threshold. The DBSCAN spatial clustering algorithm is used to cluster the two-dimensional coordinates of the target monitoring point, and the effective clusters obtained are used as the flame center. The weighted center coordinates are calculated using the temperature values ​​of the target monitoring points within the effective clusters as weights, and the weighted center coordinates and the highest temperature of the target monitoring points within the effective clusters are used as the attribute features of the flame center.

[0008] Optionally, the step of determining the behavioral features of the flame center's motion trajectory based on the attribute features of the flame center in consecutive time frames includes: Construct a time-series dataset of attribute features of the flame center under continuous time frames; Based on the aforementioned time-series dataset, the total similarity between flame centers in adjacent time frames is calculated using a space-temperature weighted algorithm. Based on the total similarity, a cost matrix is ​​constructed, and the cost matrix is ​​solved to obtain matching pairs of flame centers in adjacent time frames. Then, effective matching pairs whose total similarity meets the similarity threshold are selected from the matching pairs of flame centers in adjacent time frames. The motion trajectory is created and marked using the flame center in the first time frame of the time series dataset or the flame center that has not formed the matching pair as the starting point of the motion trajectory; Link the flame center of the current time frame in the effective matching pair to the motion trajectory corresponding to the flame center of the previous time frame, so as to update the motion trajectory; After all flame centers have been traversed, the behavioral features of the motion trajectory are extracted. The behavioral characteristics include: total trajectory displacement, displacement per unit time, average temperature, maximum temperature, temperature fluctuation variance, and number of continuous time frames of the trajectory.

[0009] Optionally, the attribute features include the weighted center coordinates and highest temperature of the flame center, and the step of calculating the total similarity between flame centers in adjacent time frames based on the time-series dataset using a spatial-temperature weighted algorithm includes: The spatial Euclidean distance between the flame centers in adjacent time frames is calculated based on the weighted center coordinates. The spatial Euclidean distance is normalized based on the maximum scale of the furnace to obtain the spatial distance similarity. The temperature similarity is obtained by calculating the relative temperature deviation of the flame center in adjacent time frames based on the highest temperature. The total similarity is obtained by weighted summation of the spatial distance similarity and the temperature similarity.

[0010] Optionally, the wall heating characteristics include at least one of the following: temperature difference between the left and right water-cooled walls of the opposed combustion boiler, temperature difference between the left and right flue gas temperatures of the low-temperature superheater, temperature difference between the left and right flue gas temperatures of the high-temperature superheater, and temperature difference between the left and right flue gas temperatures of the high-temperature reheater.

[0011] Optionally, the parameter characteristics of the left and right flue ducts of the counter-firing boiler include at least one of the following: carbon monoxide concentration deviation, oxygen content difference, flue gas flow rate, and flue duct negative pressure.

[0012] Optionally, the warning conditions that trigger the slagging warning include at least one of the following: S1: The distance between the flame center and the geometric center of the counter-firing boiler is less than the safe distance threshold, and the difference in wall temperature within a preset time is greater than or equal to the second temperature threshold. S2: The maximum wall temperature is within the slagging temperature range; S3: The amplitude and frequency of negative pressure fluctuations in the flue are greater than the corresponding threshold.

[0013] Optionally, the warning conditions that trigger the overheating warning include at least one of the following: S4: The average offset distance of the motion trajectory towards one side of the furnace is greater than or equal to the distance threshold, and the duration of the continuous offset is greater than or equal to the duration threshold. S5: The temperature difference between the left and right water-cooled walls of the counter-fired boiler is greater than or equal to the third temperature threshold. S6: The temperature difference between the flue gas temperature on the left and right sides of the low-temperature superheater is greater than or equal to the fourth temperature threshold. S7: The oxygen content difference between the left and right flues of a counter-fired boiler is greater than or equal to the oxygen content threshold. S8: The carbon monoxide concentration deviation is greater than or equal to the carbon monoxide concentration threshold.

[0014] Optionally, the warning conditions that trigger the over-temperature warning include at least one of the following: S9: The proportion of overheating points in the regional water-cooled wall is greater than or equal to the proportional threshold. S10: The temperature difference between the flue gas on the left and right sides of the high-temperature superheater and the temperature difference between the flue gas on the left and right sides of the high-temperature reheater are both greater than or equal to the fifth temperature threshold.

[0015] Optionally, the method further includes: If slagging, uneven burning, or overheating warnings are triggered, the combustion parameters and soot blowing operation parameters of the opposed combustion boiler are adjusted based on the warning results and their corresponding behavioral characteristics, wall heating characteristics, and parameter characteristics of the left and right flues of the opposed combustion boiler, in order to correct the combustion field.

[0016] Optionally, the acquisition of multi-source temperature data within the opposed-fired boiler and the parameter characteristics of the left and right flues of the opposed-fired boiler includes: The temperature distribution data inside the furnace is obtained by collecting sound wave propagation signals through an acoustic sensor array, wherein the acoustic sensor array is arranged symmetrically along the circumference of the furnace. Wall temperature distribution data are collected by fiber optic grating wall temperature sensors, wherein the fiber optic grating wall temperature sensors are deployed on key heated surfaces, including water-cooled walls, low-temperature superheaters, high-temperature superheaters, and high-temperature reheaters. By using gas sensors and pressure sensors deployed in the flue, the gas content on the left and right sides of the counter-fired boiler and the negative pressure in the flue are collected respectively, and the carbon monoxide concentration deviation and oxygen content difference are calculated based on the gas content.

[0017] According to a second aspect of this application, an early warning device for the combustion state of a counter-firing boiler is provided, the device comprising: The acquisition module is used to acquire multi-source temperature data in the counter-fired boiler and parameter characteristics of the left and right flues of the counter-fired boiler, wherein the multi-source temperature data includes furnace temperature distribution data and wall temperature distribution data. The data processing module is used to determine the wall heating characteristics based on the wall temperature distribution data; and, based on the furnace temperature distribution data, to cluster each target monitoring point in the counter-firing boiler using the DBSCAN spatial clustering algorithm, locate the flame center of the flame area, and determine the behavioral characteristics of the flame center's motion trajectory based on the attribute characteristics of the flame center in continuous time frames. The monitoring and early warning module is used to match the behavioral characteristics, the wall heating characteristics, and the parameter characteristics of the left and right flues of the opposed combustion boiler with the early warning conditions, and to issue early warnings for slagging, uneven burning, or overheating based on the matching results.

[0018] Optionally, the data processing module is specifically used to acquire three-dimensional time-series data of the flame region within the counter-firing boiler, and filter out the target monitoring points whose temperature is higher than a first temperature threshold; use the DBSCAN spatial clustering algorithm to cluster the two-dimensional coordinates of the target monitoring points, and take the effective clusters obtained by clustering as the flame center; calculate the weighted center coordinates with the temperature values ​​of the target monitoring points within the effective clusters as weights, and take the weighted center coordinates and the highest temperature of the target monitoring points within the effective clusters as the attribute features of the flame center.

[0019] Optionally, the data processing module is specifically used to construct a time-series dataset of attribute features of flame centers in continuous time frames; based on the time-series dataset, calculate the total similarity between flame centers in adjacent time frames using a spatial-temperature weighted algorithm; construct a cost matrix based on the total similarity, solve the cost matrix to obtain matching pairs of flame centers in adjacent time frames, and select valid matching pairs from the matching pairs of flame centers in adjacent time frames whose total similarity meets the similarity threshold; create and mark the motion trajectory using the flame center in the first time frame in the time-series dataset or the flame center that has not formed the matching pair as the starting point of the motion trajectory; link the flame center of the current time frame in the valid matching pair to the motion trajectory corresponding to the flame center of the previous time frame to update the motion trajectory; after all flame centers have been traversed, extract the behavioral features of the motion trajectory; wherein, the behavioral features include: total trajectory displacement, displacement per unit time, average temperature, maximum temperature, temperature fluctuation variance, and the number of consecutive time frames of the trajectory.

[0020] Optionally, the attribute features include the weighted center coordinates of the flame center and the highest temperature. The data processing module is specifically used to calculate the spatial Euclidean distance between the flame centers in adjacent time frames based on the weighted center coordinates; normalize the spatial Euclidean distance using the maximum scale of the furnace as a reference to obtain spatial distance similarity; calculate the relative temperature deviation of the flame centers in adjacent time frames based on the highest temperature to obtain temperature similarity; and perform a weighted summation of the spatial distance similarity and the temperature similarity to obtain the total similarity.

[0021] Optionally, the warning conditions that trigger the slagging warning include at least one of the following: S1: The distance between the flame center and the geometric center of the counter-firing boiler is less than the safe distance threshold, and the difference in wall temperature within a preset time is greater than or equal to the second temperature threshold. S2: The maximum wall temperature is within the slagging temperature range; S3: The amplitude and frequency of negative pressure fluctuations in the flue are greater than the corresponding threshold.

[0022] Optionally, the warning conditions that trigger the overheating warning include at least one of the following: S4: The average offset distance of the motion trajectory towards one side of the furnace is greater than or equal to the distance threshold, and the duration of the continuous offset is greater than or equal to the duration threshold. S5: The temperature difference between the left and right water-cooled walls of the counter-fired boiler is greater than or equal to the third temperature threshold. S6: The temperature difference between the flue gas temperature on the left and right sides of the low-temperature superheater is greater than or equal to the fourth temperature threshold. S7: The oxygen content difference between the left and right flues of a counter-fired boiler is greater than or equal to the oxygen content threshold. S8: The carbon monoxide concentration deviation is greater than or equal to the carbon monoxide concentration threshold.

[0023] Optionally, the warning conditions that trigger the over-temperature warning include at least one of the following: S9: The proportion of overheating points in the regional water-cooled wall is greater than or equal to the proportional threshold. S10: The temperature difference between the flue gas on the left and right sides of the high-temperature superheater and the temperature difference between the flue gas on the left and right sides of the high-temperature reheater are both greater than or equal to the fifth temperature threshold.

[0024] Optionally, the device further includes: The control module is used to adjust the combustion parameters and soot blowing operation parameters of the counter-firing boiler based on the warning result and its corresponding behavioral characteristics, the wall heating characteristics, and the parameter characteristics of the left and right flues of the counter-firing boiler, in order to correct the combustion field if slagging, uneven burning, or over-temperature warnings are triggered.

[0025] Optionally, the acquisition module is specifically used to acquire the furnace temperature distribution data through sound wave propagation signals collected by an acoustic sensor array, wherein the acoustic sensor array is symmetrically arranged circumferentially along the furnace; to acquire wall temperature distribution data through fiber optic grating wall temperature sensors, wherein the fiber optic grating wall temperature sensors are deployed on key heating surfaces, including water-cooled walls, low-temperature superheaters, high-temperature superheaters, and high-temperature reheaters; and to collect the left and right gas contents and flue negative pressure of the offset combustion boiler through gas sensors and pressure sensors deployed in the flue, and to calculate the carbon monoxide concentration deviation and oxygen content difference based on the gas contents.

[0026] According to a third aspect of this application, a readable storage medium is provided that stores a program or instructions thereon, which, when executed by a processor, implement the steps of the aforementioned method for early warning of the combustion state of a counter-fired boiler.

[0027] According to a fourth aspect of this application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method for early warning of the combustion state of a counter-fired boiler.

[0028] By employing the aforementioned technical solutions, on the one hand, multi-source early warning conditions are matched by integrating multi-source temperature data from the furnace interior and walls, as well as parameters from the left and right flues, to proactively capture abnormal trends in combustion. This enables accurate identification and early warning of three types of combustion anomalies: slagging, off-center burning, and overheating. This addresses the insufficient accuracy of traditional single-data-dimensional monitoring, improving boiler operational safety. On the other hand, the DBSCAN algorithm, which requires no pre-defined clustering, stably extracts the spatial movement behavior of the flame center from combustion noise, proactively identifying abnormal trends such as flame deviation and wall contact. This facilitates the automatic identification of multiple unequal flame centers, significantly reducing the misjudgment rate of flame center count and ensuring the safe, stable, and efficient operation of the counter-current turbine unit.

[0029] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0030] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the early warning method for the combustion state of a counter-firing boiler provided in an embodiment of this application is shown. Figure 2 A logical schematic diagram of multi-flame center clustering analysis provided in an embodiment of this application is shown; Figure 3 A logical schematic diagram of the dynamic update of the multi-flame center motion trajectory provided in an embodiment of this application is shown; Figure 4 This paper shows a structural block diagram of an early warning device for the combustion status of a counter-fired boiler provided in an embodiment of this application; Figure 5 A schematic diagram of the electronic structure of a computer device provided in an embodiment of this application is shown. Detailed Implementation

[0031] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0032] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0033] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “attached” to another element, it can be directly connected or attached to the other element, or there may be intermediate elements. Furthermore, “connected” or “attached” as used herein can include wireless connections or wireless interconnections. The term “and / or” as used herein includes all or any unit and all combinations of one or more associated listed items.

[0034] Exemplary embodiments according to this application will now be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of this application is thorough and complete, and that the concept of these exemplary embodiments is fully conveyed to those skilled in the art.

[0035] This embodiment provides an early warning method for the combustion state of a counter-fired boiler, such as... Figure 1 As shown, the method includes: Step 101: Obtain multi-source temperature data and parameter characteristics of the left and right flues of the opposed combustion boiler.

[0036] The multi-source temperature data includes furnace temperature distribution data and wall temperature distribution data. The parameter characteristics of the left and right flue gas ducts of the opposed-fired boiler include at least one of the following: carbon monoxide concentration deviation, oxygen content difference, flue gas flow rate, and flue gas negative pressure.

[0037] In practical applications, step 101, which involves acquiring multi-source temperature data within the offset combustion boiler and the parameter characteristics of the left and right flues of the offset combustion boiler, specifically includes the following steps: Step 101-1: Obtain furnace temperature distribution data by collecting sound wave propagation signals through an acoustic sensor array.

[0038] The acoustic sensor array is arranged symmetrically along the circumference of the furnace.

[0039] Step 101-2: Collect wall surface temperature distribution data using a fiber optic grating wall temperature sensor.

[0040] The fiber optic grating wall temperature sensor is deployed on key heating surfaces, including water-cooled walls, low-temperature superheaters, high-temperature superheaters, and high-temperature reheaters. The low-temperature superheater is deployed in the upper part of the vertical flue at the tail of the boiler, the high-temperature superheater is deployed in the screen area at the top of the furnace or in the inlet section of the horizontal flue, and the high-temperature reheater is deployed in the middle and rear part of the horizontal flue or in the high-temperature section of the tail vertical shaft.

[0041] Step 101-3: By using gas sensors and pressure sensors deployed in the flue, the gas content on the left and right sides of the counter-fired boiler and the negative pressure in the flue are collected respectively, and the carbon monoxide concentration deviation and oxygen content difference are calculated based on the gas content.

[0042] Specifically, gas sensors include, but are not limited to, portable flue gas analyzers or stationary flue gas analyzers.

[0043] In this embodiment, an acoustic sensor array symmetrically arranged along the circumference of the furnace accurately captures sound wave propagation signals to obtain furnace temperature distribution data. Combined with fiber optic grating wall temperature sensors deployed on key heating surfaces such as water-cooled walls and low-temperature superheaters to collect wall surface temperature distribution data, and then using gas sensors and pressure sensors in the flue to simultaneously acquire the gas content on the left and right sides and the negative pressure in the flue, and calculate the carbon monoxide concentration deviation and oxygen content difference, comprehensive and accurate acquisition of multi-dimensional key parameters of the offset combustion boiler is achieved. This not only provides rich and reliable data support for subsequent flame center positioning, combustion state characteristic analysis and anomaly early warning, but also, through the collaborative analysis of data such as gas composition deviation and temperature distribution, more comprehensively reflects the balance and stability of combustion conditions, effectively improving the sensitivity and accuracy of combustion anomaly detection, providing a solid data foundation for unit combustion optimization and adjustment and risk prediction, and helping to ensure the safe and efficient operation of the boiler.

[0044] For example, eight sets of acoustic sensor arrays are symmetrically arranged on the front and rear walls and left and right walls of the furnace. Each set contains six fiber optic acoustic sensors, covering the entire cross section of the furnace. The sampling frequency is 100Hz, and the sound wave propagation signal inside the furnace is collected. Each layer obtains 24 path temperatures, and thus obtains 4×4 area temperatures.

[0045] Fiber Bragg grating wall temperature sensors are deployed on key heating surfaces such as water-cooled walls, superheaters, and reheaters to collect real-time metal wall temperature data. Specifically, this includes 180 outlet wall temperature sensors for the low-temperature reheater, 180 outlet wall temperature sensors for the low-temperature superheater, 138 outlet wall temperature sensors for the high-temperature superheater, 838 outlet wall temperature sensors for the high-temperature reheater, 136 outlet wall temperature sensors for the screen-type superheater, 46 outlet wall temperature sensors for the rear wall of the spiral water-cooled wall, 56 outlet wall temperature sensors for the right side wall, 56 outlet wall temperature sensors for the left side wall, 68 outlet wall temperature sensors for the front wall, 193 outlet wall temperature sensors for the front wall of the vertical water-cooled wall, 162 outlet wall temperature sensors for the left wall, and 162 outlet wall temperature sensors for the right wall. There are 23 slag-condensing pipes at the outlet wall temperature, 71 at the bottom of the outlet wall temperature of the horizontal flue water-cooled wall, 20 on the left side wall of the outlet wall temperature of the horizontal flue water-cooled wall, 20 on the right side wall of the outlet wall temperature of the horizontal flue water-cooled wall, 12 on the roof of the roof superheater outlet wall temperature, 5 on the left side of the rear shaft of the roof superheater outlet wall temperature, 5 on the right side of the rear shaft of the roof superheater outlet wall temperature, 6 on the front wall of the rear shaft of the roof superheater outlet wall temperature, 6 on the rear wall of the rear shaft of the roof superheater outlet wall temperature, 6 in the middle partition wall of the rear shaft of the roof superheater outlet wall temperature, and 16 hanging pipes in the rear shaft of the roof superheater outlet wall temperature.

[0046] Step 102: Determine the wall heating characteristics based on the wall temperature distribution data.

[0047] Specifically, the wall heating characteristics include at least one of the following: temperature difference between the left and right water-cooled walls of the opposed combustion boiler, temperature difference between the left and right flue gas temperatures of the low-temperature superheater, temperature difference between the left and right flue gas temperatures of the high-temperature superheater, and temperature difference between the left and right flue gas temperatures of the high-temperature reheater. By directly reflecting the temperature differences on both sides of the key heating surfaces, the system can quickly locate the core area of ​​the imbalance in combustion energy distribution, so as to promptly detect hidden problems such as localized uneven burning and uneven heating.

[0048] It is worth mentioning that, in addition to calculating the above-mentioned wall heating characteristics, the wall temperature distribution data can also calculate the maximum wall temperature, the proportion of overheating measurement points, the wall temperature rise rate, the standard deviation of wall temperature distribution, and other wall temperature distribution characteristics, so as to help users understand the actual combustion situation of the offset combustion boiler.

[0049] Step 103: Based on the furnace temperature distribution data, the DBSCAN spatial clustering algorithm is used to cluster the target monitoring points in the counter-firing boiler, locate the flame center of the flame area, and determine the behavioral characteristics of the flame center's motion trajectory based on the attribute characteristics of the flame center in continuous time frames.

[0050] In this embodiment, the DBSCAN spatial clustering algorithm is used to cluster target monitoring points in the furnace temperature distribution data. This enables precise screening of effective high-temperature areas and elimination of noise interference, achieving accurate positioning of the flame center and solving the problems of easy interference and ambiguous positioning in traditional flame center detection. Furthermore, by tracking the motion trajectory and extracting its behavioral features through the attribute features of the flame center in continuous time frames, the system can dynamically capture key state changes such as the positional shift, temperature fluctuation, and trajectory continuity of the flame center. This not only allows the system to determine the dynamic evolution law of the combustion core area and identify latent abnormal trends such as flame deviation and unstable combustion in advance, but also provides accurate core evidence for tracing the root causes of subsequent anomalies such as slagging, off-center burning, and overheating, which helps to improve the stability and efficiency of boiler combustion.

[0051] In practical applications, step 103, based on the furnace temperature distribution data, uses the DBSCAN spatial clustering algorithm to cluster the target monitoring points in the counter-firing boiler and locate the flame center of the flame region. This specifically includes the following steps: Step 103-1a: Obtain three-dimensional time-series data of the flame region inside the counter-fired boiler, and filter out target monitoring points whose temperature is higher than the first temperature threshold.

[0052] The three-dimensional time-series data includes the x-coordinate (X), y-coordinate (Y), and temperature value (Z) of each monitoring point within multiple consecutive time frames.

[0053] Step 103-1b: The DBSCAN spatial clustering algorithm is used to cluster the two-dimensional coordinates of the target monitoring points, and the effective clusters obtained by clustering are used as the flame centers.

[0054] It should be noted that the neighborhood radius and minimum number of core points in the DBSCAN spatial clustering algorithm are dynamic and can be set reasonably according to accuracy requirements.

[0055] Step 103-1c: Calculate the weighted center coordinates using the temperature values ​​of the target monitoring points within the effective clusters as weights, and use the weighted center coordinates and the highest temperature of the target monitoring points within the effective clusters as the attribute features of the flame center.

[0056] Specifically, weighted center coordinates and The calculation formula is as follows: ; ; in, , They are respectively the first in the cluster i x-coordinate and y-coordinate of each point For the first in the cluster i Temperature values ​​at each point.

[0057] In this embodiment, before clustering, target monitoring points under high-temperature conditions are first screened based on temperature values ​​to form a set of high-temperature candidate points for each time frame. This accurately locates the flame core associated region and eliminates non-flame low-temperature interference data. For each time frame's set of high-temperature candidate points, it is determined whether it is empty. If empty, it is determined that there is no effective flame center in the opposing combustion boiler within that time frame; otherwise, it is determined that there is an effective flame center within that time frame. If an effective flame center exists, the system then uses the DBSCAN spatial clustering algorithm to adaptively cluster the two-dimensional coordinates of the target monitoring points in the high-temperature candidate point set, removing noise points marked as -1 in the clustering results and retaining effective clusters. Therefore, it can identify irregularly shaped but physically meaningful flame areas without pre-setting the number of clusters, and regard the formed high-density clusters as the flame center. It can automatically filter discrete noise points such as high-temperature dust and flue gas in the furnace without the need for additional filtering algorithms, avoid the loss of flame peak features, and ensure the accuracy and effectiveness of flame center positioning. This reduces the system's spatial positioning deviation of the flame center from ≥20cm to ≤5cm, and the noise point rejection rate reaches over 98%.

[0058] Furthermore, by calculating the weighted center coordinates using temperature as a weight, the positioning results are closer to the actual heat release center of gravity, which is more consistent with the physical nature of flame combustion. At the same time, by combining the highest temperature within the cluster as a key attribute feature, the position and intensity of the flame center are comprehensively characterized, so as to accurately and dynamically characterize the flame core state and provide a precise basis for combustion control. The deviation between the center position and the actual combustion core is reduced to within 5 cm.

[0059] Understandably, in order to facilitate the statistical analysis of multiple flame centers within each time frame, all flame centers within each time frame can be sorted in descending order of their highest temperature to form a list of multiple flame centers after sorting for each time frame, so as to facilitate the cluster analysis of multiple flame centers.

[0060] For example, such as Figure 2 As shown, firstly, target monitoring points (red dots) with temperatures higher than the first threshold are selected from the furnace temperature distribution data using a temperature threshold. Low-temperature interference data is eliminated, and the high-temperature region associated with the flame is accurately located. Using the DBSCAN spatial clustering algorithm, the target monitoring points from the previous step are clustered according to two-dimensional coordinates (X, Y). The clustering results are obtained, and noise points marked as -1 (gray dots) are eliminated, retaining only the effective clusters of different colors related to the flame. For each effective cluster, the X and Y coordinates and temperature value Z of all target monitoring points within the cluster are extracted. Using the temperature value Z as the weight, the weighted center coordinates of each cluster (white box position) are calculated. Combined with the attribute feature of the highest temperature within the cluster to form the flame center, the flame centers 1, 2, and 3 are finally output in sequence.

[0061] In practical applications, step 103, which determines the behavioral characteristics of the flame center's motion trajectory based on the attribute features of the flame center in continuous time frames, specifically includes the following steps: Step 103-2a: Construct a time-series dataset of attribute features of the flame center under continuous time frames.

[0062] Step 103-2b: Based on the time-series dataset, calculate the total similarity between flame centers in adjacent time frames using a spatial-temperature weighted algorithm.

[0063] Step 103-2c: Based on the total similarity, construct the cost matrix and solve the cost matrix to obtain the matching pairs of flame centers in adjacent time frames, and select the valid matching pairs whose total similarity meets the similarity threshold from the matching pairs of flame centers in adjacent time frames.

[0064] Step 103-2d: Using the flame center in the first time frame of the time series dataset or the flame center that has not formed a matching pair as the starting point of the motion trajectory, create and mark the motion trajectory.

[0065] Step 103-2e: Link the flame center of the current time frame that is effectively matched to the motion trajectory corresponding to the flame center of the previous time frame, so as to update the motion trajectory.

[0066] Step 103-2f: After traversing all flame centers, extract the behavioral features of the motion trajectory.

[0067] Among them, the behavioral characteristics include: total trajectory displacement, displacement per unit time, average temperature, maximum temperature, temperature fluctuation variance, and number of continuous time frames of the trajectory.

[0068] In this embodiment, a time-series dataset of flame center attribute features across consecutive time frames is first constructed. A weighted algorithm combining spatial and temperature features is used to comprehensively consider the spatial correlation and temperature consistency of flame centers in adjacent frames. The calculated total similarity is then transformed into a cost matrix. Solving this cost matrix and using a similarity threshold for filtering yields valid matching pairs. A trajectory is created starting from the flame center of the first frame or an unmatched flame center. Trajectories are continuously updated through valid matching pairs, and finally, multi-dimensional behavioral features are extracted from the complete trajectory. By dynamically tracking the trajectory evolution of the flame center, key dynamic information such as positional shifts, temperature fluctuations, and trajectory continuity is accurately captured. This solves the problem of accurate correlation between flame centers in adjacent frames, avoiding trajectory breaks or mismatches. Furthermore, multi-dimensional behavioral features comprehensively depict the dynamic changes in the core combustion region, providing valuable decision-making support for early identification of hidden anomalies such as flame shift and unstable combustion, and for tracing the root causes of anomalies. This enhances the dynamism, accuracy, and targeting of combustion monitoring.

[0069] In one embodiment, based on a time-series dataset, the total similarity between flame centers in adjacent time frames is calculated using a spatial-temperature weighted algorithm. Specifically, this includes: calculating the spatial Euclidean distance between flame centers in adjacent time frames based on weighted center coordinates; normalizing the spatial Euclidean distance using the maximum furnace scale as a reference to obtain spatial distance similarity; calculating the relative temperature deviation between flame centers in adjacent time frames based on the highest temperature to obtain temperature similarity; and weighting and summing the spatial distance similarity and temperature similarity to obtain the total similarity.

[0070] In this embodiment, the spatial Euclidean distance is calculated and normalized using weighted center coordinates, eliminating the influence of furnace scale differences and ensuring comparability and generalization ability of spatial similarity. Simultaneously, the relative deviation of the highest temperature is introduced to characterize thermal consistency, effectively reflecting the continuity of flame energy changes. The weighted fusion of these two factors yields the overall similarity, which not only improves the accuracy and stability of flame trajectory tracking but also effectively distinguishes between normal fluctuations and abnormal jumps, providing a high-precision and highly reliable data foundation for subsequent behavioral analysis of combustion status and intelligent early warning.

[0071] For example, such as Figure 3 As shown, a list of multiple flame centers across N consecutive time frames is collected, and the flame centers (different colored dots) from consecutive time frames are integrated into a time-series dataset. The flame centers for each time frame are in list format, with each element representing the attribute features of the flame center, where N ≥ 2 and is a positive integer. Two adjacent time frames in the time-series dataset are selected as the previous and current frames, and the flame center lists `prev_centers` and `curr_centers` for the previous and current time frames are extracted, respectively. For each flame center in `prev_centers` and each flame center in `curr_centers`, the similarity is calculated using a spatial-temperature dual-feature weighted method, specifically: Spatial similarity: Calculate and normalize the Euclidean distance between the two spaces to obtain the spatial distance similarity. normed distance .

[0072] The formula for calculating spatial Euclidean distance is: ; in,( x 1, y 1) represents the coordinates of the center of the flame in the previous frame. x 2, y 2) The coordinates of the flame center in the current frame; the normalization formula is: L represents the maximum spatial dimension of the furnace in a counter-firing boiler, serving as the distance normalization benchmark.

[0073] Temperature similarity: The relative temperature deviation is calculated to obtain the temperature similarity. .

[0074] The formula for calculating the relative temperature deviation is: ; The formula for temperature similarity is: ; in, t 1 represents the maximum temperature value at the center of the flame in the previous frame. t 2 represents the maximum temperature value at the center of the flame in the current frame.

[0075] The total similarity is obtained by weighted summation of spatial similarity and temperature similarity.

[0076] The formula for overall similarity is: ; in, α Spatial distance weights β As for temperature similarity weights, α + β =1, α ∈[0.6,0.8], β ∈[0.2,0.4].

[0077] Construct a similarity matrix using the total similarity, and then convert the similarity matrix into a cost matrix. The optimal matching relationship is solved using the Hungarian algorithm to obtain the matching pairs (prev_idx, curr_idx) between the flame centers of the previous and current frames. Here, prev_idx is the index of the flame center in the previous frame, and curr_idx is the index of the flame center in the current frame, which corresponds to the matching pairs of highlighted color blocks in the matrix. Valid matching pairs that meet the similarity threshold are then selected. Specifically, the similarity threshold T can be set reasonably according to the monitoring accuracy, for example, T∈[0.4,0.6]. Matching pairs with a total similarity ≥ T are considered valid matching pairs, while invalid matching pairs with a total similarity < T are discarded.

[0078] If the current time frame is the first frame of the time-series dataset, each flame center within that frame is used as the starting point of a new trajectory, and a unique trajectory ID is assigned to each new trajectory. Alternatively, for flame centers in the current time frame that do not match a flame center from the previous frame, a new trajectory ID is assigned to them, a new trajectory is constructed, and the preceding frame data for the new trajectory is filled with None, indicating that the trajectory has not been started. The initial data for each trajectory in the trajectory set consists of the attribute features of the corresponding flame center to complete trajectory initialization.

[0079] For valid matches, the flame center feature parameters corresponding to the current frame are added to the trajectory data of the corresponding trajectory ID in the previous frame and marked as "New" (green plus sign) to achieve trajectory continuation. For flame centers in the previous frame that do not match the flame center of the current frame, "None" is added to their corresponding trajectory data and marked as "Interrupted" (white cross sign). Finally, a complete flame center motion trajectory (colored curve) is formed.

[0080] For each trajectory in the trajectory set, the None value in the trajectory data is filtered out, the valid trajectory points are extracted, and dynamic monitoring indicators are calculated, including: total trajectory displacement, displacement per unit time, average temperature, maximum temperature, temperature fluctuation variance, and number of consecutive frames of the trajectory. The trajectory ID, trajectory data and dynamic monitoring indicators of each trajectory are integrated into dynamic monitoring results and output to complete the dynamic monitoring of multiple flame centers.

[0081] By using similarity calculation and the Hungarian algorithm to achieve optimal matching of flame centers in adjacent frames, the temporal trajectory of each flame center is established, solving the core problem of "flame identity association" in dynamic monitoring. It takes into account the matching of spatial location and temperature characteristics, supports the dynamic identification of flame addition / disappearance / shift, and the output displacement, temperature fluctuation and other indicators can be directly used for real-time control of combustion conditions in offset combustion boilers.

[0082] Step 104: Match the behavioral characteristics, wall heating characteristics, parameter characteristics of the left and right flues of the opposed combustion boiler with the early warning conditions, and issue early warnings for slagging, uneven burning or overheating based on the matching results.

[0083] Specifically, the warning conditions that trigger the slagging warning include at least one of the following: S1: The distance between the flame center and the geometric center of the counter-firing boiler is less than the safe distance threshold, and the difference in wall temperature within a preset time is greater than or equal to the second temperature threshold. S2: The maximum wall temperature is within the slagging temperature range; S3: The amplitude and frequency of negative pressure fluctuations in the flue are greater than the corresponding threshold.

[0084] The warning conditions that trigger the overheating warning include at least one of the following: S4: The average offset distance of the motion trajectory towards one side of the furnace is greater than or equal to the distance threshold, and the duration of the continuous offset is greater than or equal to the duration threshold. S5: The temperature difference between the left and right water-cooled walls of the counter-fired boiler is greater than or equal to the third temperature threshold. S6: The temperature difference between the flue gas temperature on the left and right sides of the low-temperature superheater is greater than or equal to the fourth temperature threshold. S7: The oxygen content difference between the left and right flues of a counter-fired boiler is greater than or equal to the oxygen content threshold. S8: The carbon monoxide concentration deviation is greater than or equal to the carbon monoxide concentration threshold.

[0085] The conditions for triggering an over-temperature warning include at least one of the following: S9: The proportion of overheating points in the regional water-cooled wall is greater than or equal to the proportional threshold. S10: The temperature difference between the flue gas on the left and right sides of the high-temperature superheater and the temperature difference between the flue gas on the left and right sides of the high-temperature reheater are both greater than or equal to the fifth temperature threshold.

[0086] It should be noted that the aforementioned reference parameters, such as the safety distance threshold, slagging temperature range, duration threshold, temperature threshold, carbon monoxide concentration threshold, oxygen content threshold, and proportion threshold, can be reasonably set based on conditions such as fuel type, furnace size, sampling density, and high and low loads. This can shorten the machine adaptation time from 2-3 days to less than 2 hours and reduce adaptation costs by more than 80%.

[0087] The early warning method for the combustion status of a counter-firing boiler provided in this application has two main advantages. Firstly, by integrating multi-source temperature data from the furnace interior and walls, as well as parameters from the left and right flues, multi-dimensional early warning conditions are matched to capture abnormal trends in the combustion status in advance. This enables accurate identification and early warning of three types of combustion anomalies: slagging, off-center burning, and overheating. This solves the problem of insufficient accuracy in early warnings based on a single data dimension in traditional monitoring, thus improving boiler operational safety. Secondly, by employing the DBSCAN algorithm, which does not require a pre-set number of clusters, the spatial motion behavior of the flame center is stably extracted from combustion noise. This allows for early identification of abnormal trends such as flame deviation and wall contact, facilitating the automatic identification of multiple unequal flame centers and significantly reducing the misjudgment rate of flame center count, ensuring the safe, stable, and efficient operation of the counter-firing unit.

[0088] In one embodiment, after step 104, the early warning method for the combustion state of the counter-fired boiler further includes: if slagging, uneven burning, or overheating is triggered, the combustion parameters and soot blowing operation parameters of the counter-fired boiler are adjusted based on the early warning result and its corresponding behavioral characteristics, wall heating characteristics, and parameter characteristics of the left and right flues of the counter-fired boiler, so as to correct the combustion field.

[0089] In this embodiment, after the offset combustion boiler triggers an early warning of slagging, uneven burning, or overheating, the combustion and soot blowing operation parameters are precisely adjusted to correct the combustion field by combining the early warning results and corresponding behavioral characteristics, wall heating characteristics, and left and right flue parameters. This enables a shift from passive handling to proactive prevention and control, which can promptly eliminate various safety hazards, avoid major failures such as heating surface tube rupture and equipment damage, optimize the furnace combustion field distribution, balance the thermal parameters of the two flues, improve boiler thermal efficiency and operational stability, reduce unplanned shutdowns, ensure continuous production, and reduce energy consumption and environmental emission risks, thus comprehensively ensuring the safe, efficient, economical, and stable operation of the boiler.

[0090] In addition, the warning level, abnormal area location, and control command execution status can be displayed in real time on the DCS operation interface, and temperature field data, combustion parameters, and soot blowing action information during the linkage control process can be recorded to form an event traceability log.

[0091] The early warning method for the combustion status of a counter-firing boiler provided in this application embodiment can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0092] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0093] Furthermore, such as Figure 4 As shown, as a specific implementation of the above-mentioned early warning method for the combustion state of a counter-fired boiler, this application embodiment provides an early warning device 400 for the combustion state of a counter-fired boiler. The early warning device 400 for the combustion state of a counter-fired boiler includes: an acquisition module 401, a data processing module 402, and a monitoring and early warning module 403.

[0094] The acquisition module 401 is used to acquire multi-source temperature data in the counter-fired boiler and parameter characteristics of the left and right flues of the counter-fired boiler. The multi-source temperature data includes furnace temperature distribution data and wall temperature distribution data. The data processing module 402 is used to determine the wall heating characteristics based on the wall temperature distribution data; and, based on the furnace temperature distribution data, to use the DBSCAN spatial clustering algorithm to cluster each target monitoring point in the counter-fired boiler, locate the flame center of the flame area, and determine the behavioral characteristics of the flame center's motion trajectory based on the attribute characteristics of the flame center in continuous time frames. The monitoring and early warning module 403 is used to match behavioral characteristics, wall heating characteristics, parameter characteristics of the left and right flues of the opposed combustion boiler with early warning conditions, and to issue early warnings for slagging, uneven burning or overheating based on the matching results.

[0095] Furthermore, the data processing module 402 is specifically used to acquire three-dimensional time-series data of the flame region inside the counter-fired boiler, and filter out target monitoring points whose temperature is higher than a first temperature threshold; use the DBSCAN spatial clustering algorithm to cluster the two-dimensional coordinates of the target monitoring points, and take the effective clusters obtained by clustering as the flame center; calculate the weighted center coordinates with the temperature value of the target monitoring points in the effective clusters as weights, and take the weighted center coordinates and the highest temperature of the target monitoring points in the effective clusters as the attribute features of the flame center.

[0096] Further, the data processing module 402 is specifically used to construct a time-series dataset of the attribute features of flame centers in continuous time frames; based on the time-series dataset, the total similarity between flame centers in adjacent time frames is calculated using a spatial-temperature weighted algorithm; based on the total similarity, a cost matrix is ​​constructed and solved to obtain matching pairs of flame centers in adjacent time frames, and effective matching pairs whose total similarity meets the similarity threshold are selected from the matching pairs of flame centers in adjacent time frames; the flame center in the first time frame in the time-series dataset or the flame center that has not formed a matching pair is used as the starting point of the motion trajectory, and the motion trajectory is created and marked; the flame center of the current time frame in the effective matching pair is linked to the motion trajectory corresponding to the flame center of the previous time frame to update the motion trajectory; after all flame centers have been traversed, the behavioral features of the motion trajectory are extracted; among which, the behavioral features include: total trajectory displacement, displacement per unit time, average temperature, maximum temperature, temperature fluctuation variance, and the number of continuous time frames of the trajectory.

[0097] Furthermore, the attribute features include the weighted center coordinates of the flame center and the highest temperature. The data processing module 402 is specifically used to calculate the spatial Euclidean distance between the flame centers in adjacent time frames based on the weighted center coordinates; normalize the spatial Euclidean distance based on the maximum scale of the furnace to obtain the spatial distance similarity; calculate the relative temperature deviation of the flame centers in adjacent time frames based on the highest temperature to obtain the temperature similarity; and perform a weighted summation of the spatial distance similarity and the temperature similarity to obtain the total similarity.

[0098] Furthermore, the warning conditions that trigger slagging warnings include at least one of the following: S1: The distance between the flame center and the geometric center of the counter-firing boiler is less than the safe distance threshold, and the difference in wall temperature within a preset time is greater than or equal to the second temperature threshold. S2: The maximum wall temperature is within the slagging temperature range; S3: The amplitude and frequency of negative pressure fluctuations in the flue are greater than the corresponding threshold.

[0099] Furthermore, the warning conditions that trigger the overheating warning include at least one of the following: S4: The average offset distance of the motion trajectory in the direction of one side of the furnace is greater than or equal to the distance threshold, and the duration of the continuous offset is greater than or equal to the duration threshold. S5: The temperature difference between the left and right water-cooled walls of the counter-fired boiler is greater than or equal to the third temperature threshold. S6: The temperature difference between the flue gas temperature on the left and right sides of the low-temperature superheater is greater than or equal to the fourth temperature threshold. S7: The oxygen content difference between the left and right flues of a counter-fired boiler is greater than or equal to the oxygen content threshold. S8: The carbon monoxide concentration deviation is greater than or equal to the carbon monoxide concentration threshold.

[0100] Furthermore, the warning conditions that trigger an over-temperature warning include at least one of the following: S9: The proportion of overheating points in the regional water-cooled wall is greater than or equal to the proportional threshold. S10: The temperature difference between the flue gas on the left and right sides of the high-temperature superheater and the temperature difference between the flue gas on the left and right sides of the high-temperature reheater are both greater than or equal to the fifth temperature threshold.

[0101] Furthermore, the early warning device 400 for the combustion status of the counter-fired boiler also includes: The control module (not shown in the figure) is used to adjust the combustion parameters and soot blowing operation parameters of the counter-fired boiler based on the warning results and their corresponding behavioral characteristics, wall heating characteristics, and parameter characteristics of the left and right flues of the counter-fired boiler if slagging, uneven burning, or over-temperature warnings are triggered, so as to correct the combustion field.

[0102] Furthermore, the acquisition module 401 is specifically used to acquire furnace temperature distribution data through acoustic wave propagation signals collected by an acoustic sensor array, wherein the acoustic sensor array is symmetrically arranged along the circumference of the furnace; to acquire wall temperature distribution data through fiber optic grating wall temperature sensors, wherein the fiber optic grating wall temperature sensors are deployed on key heating surfaces, including water-cooled walls, low-temperature superheaters, high-temperature superheaters, and high-temperature reheaters; and to collect the left and right gas contents and flue negative pressure of the offset combustion boiler through gas sensors and pressure sensors deployed in the flue, respectively, and to calculate the carbon monoxide concentration deviation and oxygen content difference based on the gas contents.

[0103] Specific limitations regarding the early warning device for the combustion status of offset-fired boilers can be found in the above-mentioned limitations on the early warning method for the combustion status of offset-fired boilers, and will not be repeated here. Each module in the aforementioned early warning device for the combustion status of offset-fired boilers can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0104] Based on the above, Figure 1Accordingly, embodiments of this application also provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 The method for early warning of combustion status in a counter-fired boiler is shown.

[0105] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0106] Based on the above, Figure 1 The method shown, and Figure 4 The virtual device embodiment shown is designed to achieve the above objectives, such as... Figure 5 As shown in the illustration, this application also provides a computer device 500, which includes a processor 501 and a memory 502. The memory 502 stores a program or instructions that can run on the processor 501. When the program or instructions are executed by the processor 501, they implement the above-described... Figure 1 The method for early warning of combustion status in a counter-fired boiler is shown.

[0107] The memory 502 can be used to store software programs and various data. The memory 502 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 502 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 502 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0108] Processor 501 may include one or more processing units; optionally, processor 501 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 501.

[0109] Computer equipment can specifically include personal computers, servers, network devices, etc.

[0110] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB ports, card reader ports, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0111] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platform, or it can be implemented by hardware.

[0113] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0114] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for early warning of combustion status in a counter-firing boiler, characterized in that, The method includes: Acquire multi-source temperature data and parameter characteristics of the left and right flues of the opposed combustion boiler, wherein the multi-source temperature data includes furnace temperature distribution data and wall temperature distribution data. The wall heating characteristics are determined based on the wall temperature distribution data. Based on the furnace temperature distribution data, the DBSCAN spatial clustering algorithm is used to cluster each target monitoring point in the counter-fired boiler, locate the flame center of the flame area, and determine the behavioral characteristics of the flame center's motion trajectory based on the attribute characteristics of the flame center in continuous time frames. The behavioral characteristics, wall heating characteristics, and parameter characteristics of the left and right flues of the opposed combustion boiler are matched with the early warning conditions, and early warnings for slagging, uneven burning, or overheating are issued based on the matching results.

2. The early warning method for the combustion state of a counter-firing boiler according to claim 1, characterized in that, Based on the furnace temperature distribution data, the DBSCAN spatial clustering algorithm is used to cluster the target monitoring points in the counter-firing boiler to locate the flame center of the flame region, including: Acquire three-dimensional time-series data of the flame region inside the counter-fired boiler, and filter out the target monitoring points whose temperature is higher than a first temperature threshold. The DBSCAN spatial clustering algorithm is used to cluster the two-dimensional coordinates of the target monitoring point, and the effective clusters obtained are used as the flame center. The weighted center coordinates are calculated using the temperature values ​​of the target monitoring points within the effective clusters as weights, and the weighted center coordinates and the highest temperature of the target monitoring points within the effective clusters are used as the attribute features of the flame center.

3. The early warning method for the combustion state of a counter-firing boiler according to claim 1, characterized in that, The behavioral features for determining the motion trajectory of the flame center based on the attribute features of the flame center in continuous time frames include: Construct a time-series dataset of attribute features of the flame center under continuous time frames; Based on the aforementioned time-series dataset, the total similarity between flame centers in adjacent time frames is calculated using a space-temperature weighted algorithm. Based on the total similarity, a cost matrix is ​​constructed, and the cost matrix is ​​solved to obtain matching pairs of flame centers in adjacent time frames. Then, effective matching pairs whose total similarity meets the similarity threshold are selected from the matching pairs of flame centers in adjacent time frames. The motion trajectory is created and marked using the flame center in the first time frame of the time series dataset or the flame center that has not formed the matching pair as the starting point of the motion trajectory; Link the flame center of the current time frame in the effective matching pair to the motion trajectory corresponding to the flame center of the previous time frame, so as to update the motion trajectory; After all flame centers have been traversed, the behavioral features of the motion trajectory are extracted. The behavioral characteristics include: total trajectory displacement, displacement per unit time, average temperature, maximum temperature, temperature fluctuation variance, and number of continuous time frames of the trajectory.

4. The early warning method for the combustion state of a counter-firing boiler according to claim 3, characterized in that, The attribute features include the weighted center coordinates of the flame center and the highest temperature. The calculation of the total similarity between flame centers in adjacent time frames based on the time-series dataset using a spatial-temperature weighted algorithm includes: The spatial Euclidean distance between the flame centers in adjacent time frames is calculated based on the weighted center coordinates. The spatial Euclidean distance is normalized based on the maximum scale of the furnace to obtain the spatial distance similarity. The temperature similarity is obtained by calculating the relative temperature deviation of the flame center in adjacent time frames based on the highest temperature. The total similarity is obtained by weighted summation of the spatial distance similarity and the temperature similarity.

5. The early warning method for the combustion state of a counter-firing boiler according to claim 1, characterized in that, The wall heating characteristics include at least one of the following: temperature difference between the left and right water-cooled walls of the opposed combustion boiler, temperature difference between the left and right flue gas temperature of the low-temperature superheater, temperature difference between the left and right flue gas temperature of the high-temperature superheater, and temperature difference between the left and right flue gas temperature of the high-temperature reheater. The parameter characteristics of the left and right flue ducts of the counter-firing boiler include at least one of the following: carbon monoxide concentration deviation, oxygen content difference, flue gas flow rate, and flue duct negative pressure.

6. The early warning method for the combustion state of a counter-firing boiler according to claim 1, characterized in that, The warning conditions that trigger a slagging warning include at least one of the following: S1: The distance between the flame center and the geometric center of the counter-firing boiler is less than the safe distance threshold, and the difference in wall temperature within a preset time is greater than or equal to the second temperature threshold. S2: The maximum wall temperature is within the slagging temperature range; S3: The amplitude and frequency of negative pressure fluctuations in the flue are greater than the corresponding threshold. The warning conditions that trigger the overheating warning include at least one of the following: S4: The average offset distance of the motion trajectory towards one side of the furnace is greater than or equal to the distance threshold, and the duration of the continuous offset is greater than or equal to the duration threshold. S5: The temperature difference between the left and right water-cooled walls of the counter-fired boiler is greater than or equal to the third temperature threshold. S6: The temperature difference between the flue gas temperature on the left and right sides of the low-temperature superheater is greater than or equal to the fourth temperature threshold. S7: The oxygen content difference between the left and right flues of a counter-fired boiler is greater than or equal to the oxygen content threshold. S8: The carbon monoxide concentration deviation is greater than or equal to the carbon monoxide concentration threshold. The conditions for triggering an over-temperature warning include at least one of the following: S9: The proportion of overheating points in the regional water-cooled wall is greater than or equal to the proportional threshold. S10: The temperature difference between the flue gas on the left and right sides of the high-temperature superheater and the temperature difference between the flue gas on the left and right sides of the high-temperature reheater are both greater than or equal to the fifth temperature threshold.

7. The early warning method for the combustion state of a counter-firing boiler according to claim 1, characterized in that, The method further includes: If slagging, uneven burning, or overheating warnings are triggered, the combustion parameters and soot blowing operation parameters of the opposed combustion boiler are adjusted based on the warning results and their corresponding behavioral characteristics, wall heating characteristics, and parameter characteristics of the left and right flues of the opposed combustion boiler, in order to correct the combustion field.

8. The early warning method for the combustion state of a counter-firing boiler according to claim 1, characterized in that, The acquisition of multi-source temperature data within the opposed-fired boiler and the parameter characteristics of the left and right flues of the opposed-fired boiler includes: The temperature distribution data inside the furnace is obtained by collecting sound wave propagation signals through an acoustic sensor array, wherein the acoustic sensor array is arranged symmetrically along the circumference of the furnace. Wall temperature distribution data are collected by fiber optic grating wall temperature sensors, wherein the fiber optic grating wall temperature sensors are deployed on key heated surfaces, including water-cooled walls, low-temperature superheaters, high-temperature superheaters, and high-temperature reheaters. By using gas sensors and pressure sensors deployed in the flue, the gas content on the left and right sides of the counter-fired boiler and the negative pressure in the flue are collected respectively, and the carbon monoxide concentration deviation and oxygen content difference are calculated based on the gas content.

9. An early warning device for the combustion state of a counter-firing boiler, characterized in that, The device includes: The acquisition module is used to acquire multi-source temperature data in the counter-fired boiler and parameter characteristics of the left and right flues of the counter-fired boiler, wherein the multi-source temperature data includes furnace temperature distribution data and wall temperature distribution data. The data processing module is used to determine the wall's heating characteristics based on the wall temperature distribution data; and, Based on the furnace temperature distribution data, the DBSCAN spatial clustering algorithm is used to cluster each target monitoring point in the counter-fired boiler, locate the flame center of the flame area, and determine the behavioral characteristics of the flame center's motion trajectory based on the attribute characteristics of the flame center in continuous time frames. The monitoring and early warning module is used to match the behavioral characteristics, the wall heating characteristics, and the parameter characteristics of the left and right flues of the opposed combustion boiler with the early warning conditions, and to issue early warnings for slagging, uneven burning, or overheating based on the matching results.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the early warning method for the combustion state of the counter-firing boiler as described in any one of claims 1 to 8.

Images