A heating furnace combustion safety risk intelligent evaluation system based on situation awareness

Abstract

The application discloses a kind of based on situation awareness's heating furnace combustion safety risk intelligent evaluation system, including multi-source situation awareness data acquisition module, coal gas calorific value measurement module, temperature heterochange identification module, abnormality determination module and safety risk assessment module;The multi-source situation awareness data acquisition module is used to synchronously collect the multi-source situation awareness data of heating furnace combustion system;The coal gas calorific value measurement module is used to receive multi-source heterogeneous data set, and obtains heat value deviation;The abnormality determination module is used to determine temperature field time series abnormal propagation relationship diagram;The safety risk assessment module can generate comprehensive combustion safety risk index, and then determine safety risk grade.The application calculates coal gas calorific value soft measurement value in real time by coal gas calorific value measurement module, and heat value deviation is obtained by dynamic comparison with heat value instrument measured value, so as to shorten coal gas calorific value detection response time, and air-fuel ratio regulation time blind area caused by combustion situation awareness lag can be effectively eliminated.

Description

Technical Field

[0001] This invention relates to the field of heating furnace safety technology, specifically to an intelligent assessment system for combustion safety risks in heating furnaces based on situational awareness. Background Technology

[0002] As a core thermal equipment in the iron and steel metallurgy and petrochemical industries, the safe and stable operation of the combustion system of the heating furnace directly affects the continuity of the production process and the stability of product quality. The system's operating status is influenced by multiple parameters, including fluctuations in the calorific value of the gas, the accuracy of the air-fuel ratio matching, changes in furnace pressure, and the uniformity of the temperature field distribution within the furnace. Therefore, in order to implement real-time, coordinated online monitoring and dynamic control of these key parameters, an intelligent assessment system for heating furnace combustion safety risks is needed to ensure combustion efficiency and production safety.

[0003] However, most existing combustion safety risk assessment systems for heating furnaces have the following technical shortcomings:

[0004] 1) The lag in gas calorific value detection leads to inaccurate air-fuel ratio adjustment, resulting in a significant time blind spot in combustion status perception;

[0005] 2) The safety assessment of the furnace temperature field remains at the static threshold level, lacking the ability to dynamically trace the spatiotemporal propagation process of temperature anomalies, making it impossible to identify and intervene in combustion safety risks in the early stages of calorific value fluctuations and the initial stages of temperature anomalies. Summary of the Invention

[0006] To address this, the present invention provides an intelligent assessment system for combustion safety risks of heating furnaces based on situational awareness, in order to solve the problems in the prior art where the detection of gas calorific value is lagging, leading to inaccurate air-fuel ratio adjustment, and the lack of dynamic source tracing capability for the spatiotemporal propagation of temperature anomalies.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A situational awareness-based intelligent assessment system for combustion safety risks in heating furnaces includes a multi-source situational awareness data acquisition module, a gas calorific value measurement module, a temperature anomaly identification module, an anomaly determination module, and a safety risk assessment module.

[0009] The multi-source situational awareness data acquisition module is used to synchronously acquire multi-source situational awareness data of the heating furnace combustion system, and sequentially perform time synchronization, spatial alignment and time delay compensation processing on the multi-source situational awareness data to obtain a multi-source heterogeneous dataset.

[0010] The gas calorific value measurement module is used to receive multi-source heterogeneous datasets, extract flue gas composition data and gas main pipe composition data at the same time, and then calculate the soft measurement value of gas calorific value; the soft measurement value of gas calorific value is dynamically compared with the measured value of calorific value meter to obtain the calorific value deviation;

[0011] The temperature anomaly identification module can extract furnace temperature field distribution data from multi-source heterogeneous datasets and perform pixel-level temporal difference operations to obtain the temperature change rate field.

[0012] The anomaly determination module can perform connected component extraction and time delay cross-correlation analysis on the temperature change rate field, identify the burner number at the onset of the temperature anomaly and the direction of anomaly propagation, and obtain a time-series anomaly propagation relationship diagram of the temperature field.

[0013] The safety risk assessment module can receive the soft measurement value of gas calorific value, calorific value deviation and temperature field time-series anomaly propagation relationship diagram output by the gas calorific value soft measurement module, and calculate the calorific value reliability risk index and temperature propagation risk index, and integrate them to generate a comprehensive combustion safety risk index, thereby determining the safety risk level.

[0014] Furthermore, the multi-source situational awareness data acquisition module includes a flue gas composition detection unit, a coal gas composition detection unit, an infrared thermal imaging unit, a valve position detection unit, and a furnace pressure detection unit.

[0015] The flue gas composition detection unit includes a laser Raman flue gas analyzer, which is installed in the main exhaust pipe of the heating furnace and the branch pipes of each combustion zone, and is used to collect flue gas composition data.

[0016] The gas composition detection unit includes an online gas chromatograph, which is installed in the gas main pipe and used to collect gas main pipe composition data;

[0017] The infrared thermal imaging unit includes an explosion-proof infrared thermal imager, which is installed on the top and tail of the heating furnace to collect data on the temperature field distribution in the furnace.

[0018] The furnace pressure detection unit includes a differential pressure transmitter, which is installed in the furnace preheating section, heating section and soaking section, and is used to collect furnace pressure data.

[0019] Furthermore, the multi-source situational awareness data acquisition module also includes a spatiotemporal reference alignment unit, which is used to unify the data collected by each detection unit in the multi-source situational awareness data acquisition module to the same time reference and spatial reference.

[0020] Furthermore, the specific details of the gas calorific value measurement module are as follows:

[0021] 1) Extract the flue gas oxygen content, flue gas carbon dioxide content, flue gas carbon monoxide content, flue gas temperature, and coal gas concentration at the same time from a multi-source heterogeneous dataset. and Volume concentration;

[0022] 2) Based on flue gas oxygen content and carbon monoxide content in flue gas Calculate the theoretical excess air coefficient This is used to indicate the degree of excess air under actual combustion conditions.

[0023] 3) Based on the theoretical excess air coefficient Calculation of soft measurement value of gas calorific value The calculation formula is as follows:

[0024]

[0025] in, This is the theoretical lower heating value of coal gas; The preset excess air coefficient; The preset compensation coefficient;

[0026] 4) After calculating the soft measurement value of the gas calorific value, combine it with the actual measured value from the calorific value analyzer. Calculate the calorific value deviation , Then, the calorific value deviation is compared with the preset deviation threshold.

[0027] Furthermore, the temperature change rate field The calculation formula is as follows:

[0028]

[0029] in, physical coordinates At the moment Temperature value; This is the sampling period of the infrared thermal imaging unit.

[0030] Furthermore, the specific content of the anomaly determination module is as follows:

[0031] 1) Extract connected components from the temperature change rate field: Set a preset rate threshold and process all pixels in the temperature change rate field one by one. Mark the pixels whose temperature change rate exceeds the threshold as abnormal pixels to obtain a set of abnormal pixels.

[0032] 2) Spatial aggregation of abnormal pixel sets is performed using a connected component labeling algorithm: abnormal pixels that are spatially adjacent and belong to the same burner influence area are aggregated into an abnormal node; each abnormal node corresponds to a specific burner influence area, and all pixels within the node belong to the same burner number.

[0033] 3) Correlation analysis of adjacent anomalous nodes: For spatially adjacent anomalous nodes... and abnormal nodes Extract the time series of temperature values ​​within each region and calculate the nodes. With nodes In time delay Cross-correlation coefficients ;

[0034] 4) Based on preset judgment conditions and cross-relation coefficients Determine if temperature anomalies originate from nodes To the node spread;

[0035] 5) By summing up all the abnormal nodes and all the directed propagation edges, we can obtain the propagation relationship diagram of the time-series anomalies in the temperature field.

[0036] Furthermore, the cross-relationship number The calculation formula is as follows:

[0037]

[0038] in, For nodes At any moment The spatial average of the temperature values ​​of all pixels within the region; For nodes At any moment The spatial average of the temperature values ​​of all pixels within the region; For nodes The mean of a temperature time series; For nodes The mean of the temperature time series.

[0039] Furthermore, the safety risk assessment module includes a calculation unit and a fusion unit; the calculation unit is capable of calculating the calorific value reliability risk index. and temperature transmission risk index The calorific value reliability risk index is used to represent the soft measurement value of coal gas calorific value. Compared to the measured value of the calorimeter And the calorific value of coal gas set as a benchmark value The degree of deviation; temperature transmission risk index Used to comprehensively assess the propagation intensity of temperature anomalies within the furnace;

[0040] The calorific value reliability risk index The calculation formula is as follows:

[0041]

[0042] in, The preset credibility weight of the calorimeter; The preset calorific value deviation risk weight;

[0043] The temperature transmission risk index The calculation formula is as follows:

[0044]

[0045] in, This represents the number of anomalous nodes in the temporal anomaly propagation diagram of the temperature field. Total number of burners; This represents the number of directed propagation edges in the temporal anomaly propagation graph of the temperature field. This is the preset maximum possible propagation length; The maximum temperature rise rate is shown in the propagation diagram. This is the preset maximum allowable temperature rise rate; , and All are weighting coefficients;

[0046] The fusion unit is capable of assessing the calorific value reliability risk index. and temperature transmission risk index Weighted fusion is performed to generate a comprehensive combustion safety risk index. Then, combined with preset risk thresholds, the safety risk levels are divided into normal, attention, warning and dangerous levels.

[0047] Furthermore, the comprehensive combustion safety risk index The calculation formula is as follows:

[0048]

[0049] in, and All are fusion weights, and satisfy the following conditions: =1.

[0050] The present invention has the following advantages: The present invention extracts the flue gas oxygen content, flue gas carbon dioxide content, flue gas carbon monoxide content, and the volume concentrations of carbon monoxide, hydrogen, and methane in the gas at the same time from a multi-source heterogeneous dataset with consistent spatiotemporal reference through a gas calorific value measurement module, and calculates the soft measurement value of the gas calorific value in real time. The calorific value deviation is obtained by dynamically comparing it with the measured value of the calorific value meter, thereby shortening the gas calorific value detection response time. It can effectively eliminate the blind spot in air-fuel ratio adjustment time caused by the lag in combustion status perception, and provide a data basis for real-time correction of air-fuel ratio.

[0051] Simultaneously, the temperature anomaly identification module performs pixel-level temporal difference calculations on the furnace temperature field distribution data to obtain the temperature change rate field. Then, the anomaly determination module extracts connected components and performs time-delay cross-correlation analysis on the temperature change rate field to construct a temperature field temporal anomaly propagation relationship graph. This identifies the burner number at the onset of the temperature anomaly and the direction of anomaly propagation, enabling dynamic tracing of furnace temperature anomalies from their inception to their entire propagation process, providing clear spatial directionality for targeted control. Combined with the safety risk assessment module, which calculates the temperature propagation risk index based on the number of anomaly nodes, the number of directed propagation edges, and the maximum temperature rise rate in the temperature field temporal anomaly propagation relationship graph, combustion safety risks can be identified and intervened in during the early calorific value fluctuation stage and the initial stage of temperature anomalies. Furthermore, targeted adjustments are made to the burner at the onset of the temperature anomaly and the direction of anomaly propagation, avoiding global interference with the normal combustion zone and improving the targeting and effectiveness of the control strategy.

[0052] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. Attached Figure Description

[0053] To more intuitively illustrate the prior art and this application, exemplary drawings are provided below. It should be understood that the specific shapes and structures shown in the drawings should not generally be regarded as limiting conditions for implementing this application; for example, based on the technical concept disclosed in this application and the exemplary drawings, those skilled in the art are able to easily make conventional adjustments or further optimizations to the addition / reduction / classification, specific shapes, positional relationships, connection methods, size ratios, etc. of certain units (components).

[0054] Figure 1 This is a module architecture diagram of an intelligent assessment system for combustion safety risks in a heating furnace based on situational awareness, according to the present invention.

[0055] Figure 2 This is a flowchart illustrating the implementation of the safety risk assessment module in a situational awareness-based intelligent assessment system for combustion safety risks in a heating furnace, as described in this invention. Detailed Implementation

[0056] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these embodiments are merely for further explanation of the present invention and should not be construed as limiting the scope of protection of the present invention. Technical engineers in the field can make some non-essential improvements and adjustments to the present invention based on the above-described content. 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.

[0057] Please see Figure 1 A situational awareness-based intelligent assessment system for combustion safety risks in heating furnaces includes a multi-source situational awareness data acquisition module, a gas calorific value measurement module, a temperature anomaly identification module, an anomaly determination module, and a safety risk assessment module.

[0058] The multi-source situational awareness data acquisition module is used to synchronously acquire multi-source situational awareness data of the heating furnace combustion system, and sequentially perform time synchronization, spatial alignment, and time delay compensation processing on the data to obtain a multi-source heterogeneous dataset. The multi-source situational awareness data includes flue gas composition data, main gas pipe composition data, and furnace temperature field distribution data; the flue gas composition data includes flue gas oxygen content, flue gas carbon dioxide content, and flue gas carbon monoxide content; the main gas pipe composition data includes the content of... and Volume concentration.

[0059] The multi-source situational awareness data acquisition module includes a flue gas composition detection unit, a coal gas composition detection unit, an infrared thermal imaging unit, a valve position detection unit, and a furnace pressure detection unit. Each detection unit is equipped with its own sampling clock to facilitate synchronous sampling and ensure the consistency of the acquired data in time.

[0060] The flue gas composition detection unit includes a laser Raman flue gas analyzer, which is installed in the main exhaust pipe of the heating furnace and the branch pipes of each combustion section to collect flue gas composition data, including flue gas oxygen content, flue gas carbon dioxide content, flue gas carbon monoxide content and flue gas temperature.

[0061] The gas composition detection unit includes an online gas chromatograph, installed in the main gas pipe, used to collect composition data of the main gas pipe, including the composition of the gas. Volume concentration, Volume concentration and Volume concentration.

[0062] The infrared thermal imaging unit includes an explosion-proof infrared thermal imager, which is installed on the top and tail of the heating furnace to collect furnace temperature field distribution data. The image frame rate is 1Hz-5Hz, the temperature measurement range is 300℃-1500℃, and the output temperature field matrix data is output.

[0063] The furnace pressure detection unit includes a differential pressure transmitter, which is installed in the furnace preheating section, heating section and soaking section to collect furnace pressure data.

[0064] The multi-source situational awareness data acquisition module also includes a spatiotemporal reference alignment unit, which unifies the data acquired by each detection unit in the multi-source situational awareness data acquisition module to the same time and spatial reference. This unit uses the sampling clock of the furnace pressure detection unit as the master clock, and synchronizes the acquisition clocks of the flue gas composition detection unit, coal gas composition detection unit, infrared thermal imaging unit, and valve position detection unit to the master clock through the IEEE 1588 precise time protocol, and adds a unified timestamp to each frame of acquired data, thereby ensuring the consistency of data from different sources in the time dimension.

[0065] For the furnace temperature field distribution data acquired by the infrared thermal imaging unit, the spatiotemporal reference alignment unit performs viewpoint distortion correction and pixel-physical coordinate mapping. First, several temperature measurement reference points with known physical coordinates are set within the furnace. The infrared thermal imager is used to calibrate the pixel coordinates of these reference points in the temperature field image, establishing a correspondence between the image pixel coordinates and the physical coordinates within the furnace. Each physical coordinate is then associated with its corresponding burner number, thus obtaining the burner's influence area. This ensures that each pixel value in the furnace temperature field distribution data corresponds to a specific physical spatial coordinate within the furnace and the burner number to which that coordinate belongs.

[0066] For the flue gas composition data collected by the flue gas composition detection unit, the spatiotemporal reference alignment unit calculates the transmission time delay based on the flue gas velocity and the sampling pipe length. Subtract the transmission delay from the timestamp of the flue gas composition data collected at the current moment. This yields a timestamp after time delay compensation, aligning the flue gas composition data with the actual combustion state within the furnace. (Transmission time delay) The calculation formula is as follows:

[0067]

[0068] in, Sampling pipe length; The volumetric flow rate of the flue gas in the sampling pipeline; This represents the cross-sectional area of ​​the sampling pipe.

[0069] After completing the above processing, the spatiotemporal reference alignment unit encapsulates the time synchronization marker, the furnace temperature field distribution data after distortion correction, the flue gas composition data after time delay compensation, and the gas main pipe composition data into a spatiotemporal reference consistent multi-source heterogeneous dataset.

[0070] The gas calorific value measurement module receives multi-source heterogeneous datasets and extracts flue gas composition data and main gas pipeline composition data from them at the same time. It then calculates the soft-measurement value of the gas calorific value. This soft-measurement value is dynamically compared with the measured value from the calorific value analyzer to obtain the calorific value deviation. This provides real-time calorific value data for subsequent combustion safety risk assessment and air-fuel ratio correction. The specific contents of the gas calorific value measurement module are as follows:

[0071] 1) Extract the flue gas oxygen content, flue gas carbon dioxide content, flue gas carbon monoxide content, flue gas temperature, and coal gas concentration at the same time from a multi-source heterogeneous dataset. and Volume concentration.

[0072] 2) Based on flue gas oxygen content and carbon monoxide content in flue gas Calculate the theoretical excess air coefficient This is used to indicate the degree of excess air under actual combustion conditions. The calculation formula is as follows:

[0073]

[0074] Where 21 represents the volume percentage of oxygen in the air; and 0.5 represents the stoichiometric coefficient of oxygen consumed by the combustion of carbon monoxide and the volume of carbon monoxide.

[0075] 3) Based on the theoretical excess air coefficient Calculation of soft measurement value of gas calorific value The calculation formula is as follows:

[0076]

[0077] in, This is the theoretical lower heating value of coal gas; The preset excess air coefficient; This is a preset compensation coefficient used to correct system deviations caused by undetected trace components in the coal gas.

[0078] Theoretical lower heating value of coal gas The calculation formula is as follows:

[0079]

[0080] in, for Low heating value; for Low heating value; for Low heating value; For coal gas Volume concentration; For coal gas Volume concentration; For coal gas Volume concentration.

[0081] 4) After calculating the soft measurement value of the gas calorific value, combine it with the actual measured value from the calorific value analyzer. Calculate the calorific value deviation , Then compare the calorific value deviation with the preset deviation threshold:

[0082] If the calorific value deviation continues to exceed the preset deviation threshold, a calorific value calibration prompt will be triggered, prompting the operator to calibrate and maintain the calorific value to ensure the reliability of the measured values.

[0083] If the calorific value deviation does not exceed the preset deviation threshold, the calorific value meter calibration prompt will not be triggered, indicating that the consistency between the measured value of the calorific value meter and the soft measurement value of the calorific value of the gas meets the requirements, and the measured value of the calorific value meter can continue to be used as a reference for air-fuel ratio control.

[0084] The temperature anomaly identification module can extract furnace temperature field distribution data from multi-source heterogeneous datasets and perform pixel-level temporal difference operations to obtain the temperature change rate field. This method facilitates the representation of the intensity of dynamic temperature changes at various physical coordinates within the furnace. The calculation formula is as follows:

[0085]

[0086] in, physical coordinates At the moment Temperature value; This is the sampling period of the infrared thermal imaging unit.

[0087] The anomaly detection module can perform connected component extraction and time-delay cross-correlation analysis on the temperature change rate field, identify the burner number at the onset of the temperature anomaly and the direction of anomaly propagation, and obtain a time-series anomaly propagation relationship diagram of the temperature field. The specific contents of the anomaly detection module are as follows:

[0088] 1) Extract connected components from the temperature change rate field:

[0089] A preset rate threshold is set, which is determined based on the upper limit of the furnace temperature fluctuation range under normal combustion conditions. All pixels in the temperature change rate field are processed one by one, and pixels whose temperature change rate exceeds the threshold are marked as abnormal pixels, resulting in a set of abnormal pixels.

[0090] 2) Spatial aggregation of abnormal pixel sets is performed using a connected component labeling algorithm:

[0091] Abnormal pixels that are spatially adjacent and belong to the same burner influence area are grouped into an abnormal node. Each abnormal node corresponds to a specific burner influence area, and all pixels within the node belong to the same burner number.

[0092] The aforementioned connected component labeling algorithm generally refers to an image processing algorithm that merges spatially adjacent pixels that meet the same labeling condition into the same connected region in a binary or labeled image. It is mainly used to spatially aggregate the set of abnormal pixels in the temperature change rate field where the temperature change rate exceeds a preset rate threshold. The algorithm can also be any one of the following: region growing method, connected component analysis method based on pixel adjacency relationship, connected component extraction algorithm based on graph theory, or morphological connected component labeling algorithm. Its working principle is as follows: taking the abnormal pixels as foreground pixels and the non-abnormal pixels as background pixels, all pixels in the temperature change rate field are processed one by one according to the preset adjacency criteria (such as 4 adjacency or 8 adjacency), and the abnormal pixels that are spatially adjacent and belong to the same burner influence area are merged into the same abnormal node, thereby ensuring that each abnormal node corresponds to a certain burner influence area, and all abnormal pixels in the node have the same burner number.

[0093] 3) Correlation analysis of adjacent abnormal nodes:

[0094] For spatially adjacent abnormal nodes and abnormal nodes Extract the time series of temperature values ​​within each region and calculate the nodes. With nodes In time delay Cross-correlation coefficients The calculation formula is as follows:

[0095]

[0096] in, For nodes At any moment The spatial average of the temperature values ​​of all pixels within the region; For nodes At any moment The spatial average of the temperature values ​​of all pixels within the region; For nodes The mean of a temperature time series; For nodes The mean of the temperature time series.

[0097] 4) Based on preset judgment conditions and cross-relation coefficients Determine if temperature anomalies originate from nodes To the node Propagation. If the cross-relationship number If all of the following conditions are met, a temperature anomaly is determined to originate from a node. To the node Propagate and establish from nodes To the node The directed propagation edge.

[0098] The preset judgment conditions are as follows:

[0099] a) Cross-correlation coefficient In time delay The maximum value is obtained at that point.

[0100] b) Cross-correlation coefficient , i.e., node Temperature changes lag behind nodes .

[0101] c) Cross-correlation coefficient Within the preset physical propagation speed range, i.e., the spatial distance between nodes divided by the cross-correlation coefficient. The obtained propagation velocity conforms to the physically reasonable range of heat propagation in the furnace, which is calibrated based on the furnace structure and historical operating data.

[0102] d) Maximum cross-correlation coefficient The correlation coefficient exceeds a preset threshold to exclude spurious correlations caused by random fluctuations.

[0103] 5) By summing up all anomalous nodes and all directed propagation edges, a propagation relationship diagram of the temperature field time-series anomaly is obtained. This propagation relationship diagram consists of anomalous nodes as vertices and directed propagation edges as connections, reflecting the propagation path of temperature anomalies within the furnace space.

[0104] Please see Figure 2 The safety risk assessment module can receive the soft measurement values ​​of gas calorific value, calorific value deviation, and temperature field time-series anomaly propagation relationship diagram output by the gas calorific value soft measurement module, and calculate the calorific value confidence risk index and temperature propagation risk index. It then integrates these to generate a comprehensive combustion safety risk index, thereby determining the safety risk level and executing the corresponding graded linkage control strategy.

[0105] The safety risk assessment module includes a calculation unit and a fusion unit. The calculation unit is capable of calculating the calorific value reliability risk index. and temperature transmission risk index The calorific value reliability risk index is used to represent the soft measurement value of coal gas calorific value. Compared to the measured value of the calorimeter And the calorific value of coal gas set as a benchmark value The degree of deviation. Temperature transmission risk index. Used to comprehensively assess the propagation intensity of temperature anomalies within the furnace. Calorific value reliability risk index. The calculation formula is as follows:

[0106]

[0107] in, The preset credibility weight of the calorimeter; The preset calorific value deviation risk weight.

[0108] Temperature transmission risk index The calculation formula is as follows:

[0109]

[0110] in, This represents the number of anomalous nodes in the temporal anomaly propagation diagram of the temperature field. Total number of burners; This represents the number of directed propagation edges in the temporal anomaly propagation graph of the temperature field. This is the preset maximum possible propagation length; The maximum temperature rise rate is shown in the propagation diagram. This is the preset maximum allowable temperature rise rate; , and All are weighting coefficients. .

[0111] The fusion unit can assess the calorific value reliability risk index. and temperature transmission risk index Weighted fusion is performed to generate a comprehensive combustion safety risk index. Then, combining preset risk thresholds, the safety risk levels are divided into normal, attention, warning, and dangerous levels, and a graded linkage control strategy is implemented. The calculation formula is as follows:

[0112]

[0113] in, and All are fusion weights, and satisfy the following conditions: =1.

[0114] Combined with preset risk thresholds , and Determine the level of safety risk ( ):

[0115] when If the safety risk level is determined to be normal, the soft measurement value of the gas calorific value is used instead of the actual measured value of the calorific value meter in the calculation of the air-fuel ratio. The PLC control system performs feedforward compensation on the opening of the gas main regulating valve according to the real-time changes of the soft measurement value of the gas calorific value, and the compensation direction is to maintain the stability of the air-fuel ratio.

[0116] when If the safety risk level is determined to be at the concern level, the supply of combustion air will be increased by 2%-4%, and the air-fuel ratio setting value of each section will be dynamically adjusted according to the soft measurement value of the gas calorific value in order to suppress the impact of calorific value fluctuations on combustion stability.

[0117] when If the safety risk level is determined to be warning level, then based on the burner number at the start of the temperature anomaly and the direction of the anomaly propagation, the opening of the combustion air branch valve of the burner and the adjacent burner downstream along the direction of the anomaly propagation is increased by 5%-10%, while the flow rate of the main gas pipe is reduced by 3%-5% to block the path of the temperature anomaly propagation.

[0118] when If the safety risk level is determined to be dangerous, immediately shut off the quick-cut valve of the main gas pipe, close the burner valves of each branch pipe, start the induced draft fan at its maximum frequency, and open the furnace emergency vent valve to prevent excessive positive pressure in the furnace from causing gas leakage or backfire.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A situational awareness-based intelligent assessment system for combustion safety risks in heating furnaces, characterized in that, It includes a multi-source situational awareness data acquisition module, a gas calorific value measurement module, a temperature anomaly identification module, an anomaly determination module, and a safety risk assessment module; The multi-source situational awareness data acquisition module is used to synchronously acquire multi-source situational awareness data of the heating furnace combustion system, and sequentially perform time synchronization, spatial alignment and time delay compensation processing on the multi-source situational awareness data to obtain a multi-source heterogeneous dataset. The gas calorific value measurement module is used to receive multi-source heterogeneous datasets, extract flue gas composition data and gas main pipe composition data at the same time, and then calculate the soft measurement value of gas calorific value; the soft measurement value of gas calorific value is dynamically compared with the measured value of calorific value meter to obtain the calorific value deviation; The temperature anomaly identification module can extract furnace temperature field distribution data from multi-source heterogeneous datasets and perform pixel-level temporal difference operations to obtain the temperature change rate field. The anomaly determination module can perform connected component extraction and time delay cross-correlation analysis on the temperature change rate field, identify the burner number at the onset of the temperature anomaly and the direction of anomaly propagation, and obtain a time-series anomaly propagation relationship diagram of the temperature field. The safety risk assessment module can receive the soft measurement value of gas calorific value, calorific value deviation and temperature field time-series anomaly propagation relationship diagram output by the gas calorific value soft measurement module, and calculate the calorific value reliability risk index and temperature propagation risk index, and integrate them to generate a comprehensive combustion safety risk index, thereby determining the safety risk level.

2. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 1, characterized in that, The multi-source situational awareness data acquisition module includes a flue gas composition detection unit, a coal gas composition detection unit, an infrared thermal imaging unit, a valve position detection unit, and a furnace pressure detection unit. The flue gas composition detection unit includes a laser Raman flue gas analyzer, which is installed in the main exhaust pipe of the heating furnace and the branch pipes of each combustion zone, and is used to collect flue gas composition data. The gas composition detection unit includes an online gas chromatograph, which is installed in the gas main pipe and used to collect gas main pipe composition data; The infrared thermal imaging unit includes an explosion-proof infrared thermal imager, which is installed on the top and tail of the heating furnace to collect data on the temperature field distribution in the furnace. The furnace pressure detection unit includes a differential pressure transmitter, which is installed in the furnace preheating section, heating section and soaking section, and is used to collect furnace pressure data.

3. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 1, characterized in that, The multi-source situational awareness data acquisition module also includes a spatiotemporal reference alignment unit, which is used to unify the data collected by each detection unit in the multi-source situational awareness data acquisition module to the same time reference and spatial reference.

4. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 1, characterized in that, The specific contents of the gas calorific value measurement module are as follows: 1) Extract the flue gas oxygen content, flue gas carbon dioxide content, flue gas carbon monoxide content, flue gas temperature, and coal gas concentration at the same time from a multi-source heterogeneous dataset. and Volume concentration; 2) Based on flue gas oxygen content and carbon monoxide content in flue gas Calculate the theoretical excess air coefficient This is used to indicate the degree of excess air under actual combustion conditions. 3) Based on the theoretical excess air coefficient Calculation of soft measurement value of gas calorific value The calculation formula is as follows: in, This is the theoretical lower heating value of coal gas; The preset excess air coefficient; The preset compensation coefficient; 4) After calculating the soft measurement value of the gas calorific value, combine it with the actual measured value from the calorific value analyzer. Calculate the calorific value deviation , Then, the calorific value deviation is compared with the preset deviation threshold.

5. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 1, characterized in that, The temperature change rate field The calculation formula is as follows: in, physical coordinates At the moment Temperature value; This represents the sampling period of the infrared thermal imaging unit.

6. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 1, characterized in that, The specific content of the anomaly determination module is as follows: 1) Extract connected components from the temperature change rate field: Set a preset rate threshold and process all pixels in the temperature change rate field one by one. Mark the pixels whose temperature change rate exceeds the threshold as abnormal pixels to obtain a set of abnormal pixels. 2) Spatial aggregation of abnormal pixel sets is performed using a connected component labeling algorithm: abnormal pixels that are spatially adjacent and belong to the same burner influence area are aggregated into an abnormal node; each abnormal node corresponds to a specific burner influence area, and all pixels within the node belong to the same burner number. 3) Correlation analysis of adjacent anomalous nodes: For spatially adjacent anomalous nodes... and abnormal nodes Extract the time series of temperature values ​​within each region and calculate the nodes. With nodes In time delay Cross-correlation coefficients ; 4) Based on preset judgment conditions and cross-relation coefficients Determine if temperature anomalies originate from nodes To the node spread; 5) By summing up all the abnormal nodes and all the directed propagation edges, we can obtain the propagation relationship diagram of the time series anomalies in the temperature field.

7. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 6, characterized in that, The cross-relationship number The calculation formula is as follows: in, For nodes At any moment The spatial average of the temperature values ​​of all pixels within the region; For nodes At any moment The spatial average of the temperature values ​​of all pixels within the region; For nodes The mean of a temperature time series; For nodes The mean of the temperature time series.

8. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness according to claim 1, characterized in that, The safety risk assessment module includes a calculation unit and a fusion unit; the calculation unit is capable of calculating the calorific value reliability risk index. and temperature transmission risk index ; The calorific value reliability risk index is used to represent the soft measurement value of coal gas calorific value. Compared to the measured value of the calorimeter And the calorific value of coal gas set as a benchmark value The degree of deviation; Temperature transmission risk index Used to comprehensively assess the propagation intensity of temperature anomalies within the furnace; The calorific value reliability risk index The calculation formula is as follows: in, The preset credibility weight of the calorimeter; The preset calorific value deviation risk weight; The temperature transmission risk index The calculation formula is as follows: in, This represents the number of anomalous nodes in the temporal anomaly propagation diagram of the temperature field. Total number of burners; This represents the number of directed propagation edges in the temporal anomaly propagation graph of the temperature field. The maximum possible propagation length is preset. The maximum temperature rise rate is shown in the propagation diagram. The preset maximum allowable temperature rise rate; , and All are weighting coefficients; The fusion unit is capable of assessing the calorific value reliability risk index. and temperature transmission risk index A weighted fusion is performed to generate a comprehensive combustion safety risk index. Then, combined with preset risk thresholds, the safety risk levels are divided into normal, attention, warning and dangerous levels.

9. The intelligent assessment system for combustion safety risks of a heating furnace based on situational awareness as described in claim 8, characterized in that, The comprehensive combustion safety risk index The calculation formula is as follows: in, and All are fusion weights, and satisfy the following conditions: =1.

Images