Combustion safety management and control system and method

Abstract

The invention relates to the technical field of combustion safety management and control, and discloses a combustion safety management and control system and method, and the system comprises an acquisition module which is used for collecting spectral data in real time, processing and analyzing the spectral data, obtaining real-time key parameters, and calculating a real-time combustion evaluation value according to the real-time key parameters; the judgment module is used for judging whether management and control are needed or not according to the real-time combustion evaluation value, and if yes, a plurality of real-time management and control characteristics and corresponding parameters needing to be adjusted are determined; the generation module is used for generating a to-be-controlled parameter of each parameter needing to be adjusted based on the control parameter-key parameter dependency model and obtaining a plurality of first management and control strategies; and the management and control module is used for performing management and control simulation on the plurality of first management and control strategies, determining a second management and control strategy according to a simulation result, issuing a management and control instruction, accurately evaluating a parameter state, formulating a reasonable management and control strategy and improving combustion safety management and control efficiency.

Description

Technical Field

[0001] This application relates to the field of combustion safety control technology, and in particular to a combustion safety control system and method. Background Technology

[0002] In industrial combustion processes, such as boiler combustion, effective combustion safety management is crucial. Currently, traditional combustion detection and control methods have many shortcomings. For example, they cannot detect abnormalities in key combustion parameters in a timely manner, nor can they formulate reasonable control strategies. This leads to problems such as uneven boiler combustion, localized overheating of heating surfaces, high-temperature corrosion, ash accumulation, and high NOx levels, seriously affecting the safe and stable operation of combustion equipment and energy utilization efficiency. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides a combustion safety control system and method. By collecting real-time key parameters and calculating real-time combustion evaluation values, the system determines whether control is needed based on these values. If so, it identifies several real-time control characteristics and corresponding parameters requiring adjustment, and combines these with a control parameter-key parameter dependency model to obtain several first control strategies. The system then performs control simulations on these first control strategies, determines second control strategies, and issues control instructions. This accurately assesses parameter states and formulates reasonable control strategies, thereby improving the efficiency of combustion safety control.

[0004] In some embodiments of this application, a combustion safety control system is provided, including: The acquisition module is used to acquire, process, and analyze spectral data in real time to obtain real-time key parameters and calculate real-time combustion evaluation values ​​based on these parameters. The judgment module is used to determine whether control is needed based on the real-time combustion evaluation value. If so, it determines several real-time control features and the corresponding parameters that need to be adjusted. The generation module is used to generate the control parameters to be adjusted for each parameter based on the control parameter-key parameter dependency model, and to obtain several first control strategies. The control module is used to simulate the control of several first control strategies, determine the second control strategy based on the simulation results, and issue control instructions.

[0005] In some embodiments of this application, calculating a real-time combustion evaluation value based on real-time key parameters includes: Several combustion evaluation indicators are preset, and each combustion evaluation indicator is mapped to several preset combustion characteristics; The correlation analysis was performed between several preset combustion characteristics of each combustion evaluation index and real-time key parameters to obtain the degree of correlation. Real-time key parameters with a correlation degree greater than a preset correlation degree threshold are set as correlation parameters of the corresponding preset combustion characteristics, and weight coefficients of the corresponding correlation parameters are set. Sequentially set the correlation parameters of several preset combustion characteristics for each combustion evaluation index; The associated parameters of each preset combustion feature are compared with the corresponding standard parameter range. If they are within the standard parameter range, the state coefficient of the corresponding key parameter is generated according to the first calculation formula. If they are not within the standard parameter range, the state coefficient of the corresponding key parameter is generated according to the second calculation formula. The first combustion evaluation coefficient corresponding to the preset combustion feature is generated based on the state coefficient of the associated parameters of the same preset combustion feature; The second combustion evaluation coefficient of the corresponding combustion evaluation index is generated based on the first combustion evaluation coefficient of several preset combustion characteristics of the same combustion evaluation index and the corresponding weight coefficient. Real-time combustion evaluation values ​​are generated based on the second combustion evaluation coefficients of several combustion evaluation indicators and their corresponding weighting coefficients.

[0006] In some embodiments of this application, a determination is made based on the real-time combustion evaluation value to determine whether control is required. If so, several real-time control features and corresponding parameters to be adjusted are determined, including: Pre-set combustion evaluation thresholds; If the real-time combustion evaluation value is greater than the combustion evaluation value threshold, it is determined that no control is needed. If the real-time combustion evaluation value is not greater than the combustion evaluation value threshold, it is determined that control measures are needed. If control is required, select the combustion evaluation indicators to be optimized and set the number of control features for each combustion evaluation indicator to be optimized. Construct a sequence of undetermined control features for each combustion evaluation index to be optimized, and determine the real-time control features based on the number of control features; Set the number of adjustment parameters for each real-time control feature; Construct a sequence of undetermined adjustment parameters for each real-time control feature, and determine the parameters that need to be adjusted for the real-time control feature based on the number of adjustment parameters.

[0007] In some embodiments of this application, determining several real-time control features and corresponding parameters to be adjusted further includes: The preset second combustion evaluation coefficient threshold, the preset first combustion evaluation coefficient threshold, and the state coefficient threshold of each associated parameter are pre-set for each combustion evaluation index; Combustion evaluation indicators whose second combustion evaluation coefficient is less than the corresponding preset second combustion evaluation coefficient threshold are selected and set as combustion evaluation indicators to be optimized. Select the preset combustion features whose first combustion evaluation coefficient is less than the corresponding preset first combustion evaluation coefficient threshold in each combustion evaluation index to be optimized, and set them as features to be controlled. Construct a sequence of undetermined control features for each combustion evaluation index to be optimized, wherein the undetermined control features in the sequence are arranged according to their weight coefficients. The number of control features for each combustion evaluation indicator to be optimized is set according to the weight coefficient of each combustion evaluation indicator to be optimized and the difference between the corresponding second combustion evaluation value coefficients. Based on the number of control features, feature extraction is performed on the undetermined control feature sequence of the corresponding combustion evaluation index to be optimized, and real-time control features are determined based on the extraction results; The number of adjustment parameters for each real-time control feature is set according to the weight coefficient of each real-time control feature and the corresponding state coefficient difference. Based on the number of adjustment parameters, extract parameters from the sequence of undetermined adjustment parameters for the corresponding real-time control features, and determine the parameters to be adjusted for the real-time control features based on the extraction results.

[0008] In some embodiments of this application, the control parameter-key parameter dependency model includes: Obtain historical control logs, extract the historical control node for each historical control parameter in each historical control log, and obtain the corresponding historical control quantity value; Set the historical monitoring period for each historical control parameter's historical control node; Obtain the historical change characteristics of each key parameter in the historical monitoring period of each historical control node, and generate historical change evaluation values; Key parameters whose historical change evaluation values ​​are greater than the preset change evaluation value threshold are set as undetermined dependent key parameters of the corresponding historical control parameters; Pre-set several control value ranges; Multiple historical control values ​​of the same historical control parameter from different historical control logs are assigned to the corresponding control value ranges. The first comparison is made of several undetermined key parameters corresponding to different historical control values ​​in the same control value range to obtain the frequency of occurrence of each undetermined key parameter. Remove undetermined dependent key parameters whose frequency of occurrence is less than a preset frequency threshold, and construct a control quantity value-change evaluation value matrix based on the historical change evaluation values ​​corresponding to the remaining undetermined dependent key parameters in different control quantity value ranges. Based on the control value-change evaluation value matrix, the historical control value sequence and the historical change evaluation value sequence of several undetermined critical coefficients are obtained. The dependence coefficient of each historical change evaluation value sequence on the historical control value sequence is calculated. Set the undetermined key parameters of the historical change evaluation value sequence with a dependency coefficient greater than the preset dependency coefficient threshold as the key parameters of the corresponding historical control parameters. Several dependent key parameters for each historical control parameter are generated sequentially; Construct a dependency key parameter-control parameter mapping table, where each dependency key parameter is mapped to several control parameters; Using each key parameter and its corresponding historical change features as training input data, and the control parameters mapped to each key parameter and their historical control values ​​as training output data, a neural network is trained to obtain a control parameter-key parameter dependency model.

[0009] In some embodiments of this application, before generating the control parameters to be adjusted for each parameter based on the control parameter-key parameter dependency model and obtaining several first control strategies, the process includes: The number of first combustion evaluation coefficients to be optimized for each control feature is determined based on the difference in the second combustion evaluation coefficients for each evaluation indicator to be optimized, the number of corresponding control features, and the weight coefficients corresponding to the control features. The number of state systems to be optimized for each control feature is determined based on the number of first combustion evaluation systems to be optimized for each control feature, the number of corresponding adjustment parameters, and the weight coefficients corresponding to the parameters to be adjusted. The required adjustment value for each parameter is determined based on the quantity of the state system to be optimized for each parameter.

[0010] In some embodiments of this application, the control parameters to be controlled for each parameter that needs adjustment are generated based on a control parameter-key parameter dependency model, resulting in several first control strategies, including: Each parameter that needs adjustment and its corresponding adjustment value are input into the control parameter-key parameter dependency model to obtain several parameters to be controlled for each parameter that needs adjustment and the control value of each parameter to be controlled. Randomly select each parameter to be adjusted as the target parameter to be controlled; Construct a first control strategy based on all target parameters that need to be adjusted; Several primary control strategies are generated.

[0011] In some embodiments of this application, control simulation is performed on several first control strategies, including: Intelligent algorithms are used to process and analyze spectral data to obtain real-time temperature field data; It can intuitively display the temperature distribution at different locations inside the furnace, and construct a combustion condition simulation model based on combustion digital twin technology and real-time temperature field data; Based on the combustion condition simulation model, control simulations were performed for each first control strategy, and simulation results for each first control strategy were obtained. The simulation results include simulated change characteristics of several parameters that need to be adjusted.

[0012] In some embodiments of this application, a second control strategy is determined based on simulation results, and control instructions are issued, including: Calculate the simulation state coefficient of the corresponding parameter to be adjusted based on the simulation change value in the simulation change characteristics of each parameter to be adjusted; The simulation compensation coefficients are generated based on the simulated rate of change and the simulated trend of change in the simulated change characteristics. The simulated first combustion evaluation coefficient for the corresponding control characteristics is calculated based on the simulated state coefficient, the simulated compensation coefficient, and the weight coefficients of the corresponding parameters to be adjusted. Based on the simulated first combustion evaluation coefficient of several control features of the same combustion evaluation index to be optimized and the weight coefficient of the corresponding control features, a simulated second combustion evaluation coefficient of the corresponding combustion evaluation index to be optimized is generated. The simulated combustion evaluation value is generated based on the simulated second combustion evaluation coefficients of several combustion evaluation indicators to be optimized, the weight coefficients of the corresponding combustion evaluation indicators to be optimized, and the second combustion evaluation coefficients of other combustion evaluation indicators. The simulated combustion evaluation values ​​of all the first control strategies are sorted, the second control strategy is determined based on the sorting results, and control instructions are issued according to the second control strategy.

[0013] In some embodiments of this application, a combustion safety control method is also included: Real-time acquisition, processing, and analysis of spectral data are used to obtain real-time key parameters, and real-time combustion evaluation values ​​are calculated based on these parameters. Determine whether control is needed based on real-time combustion evaluation values. If so, identify several real-time control features and corresponding parameters that need to be adjusted. Based on the control parameter-key parameter dependency model, the control parameters to be adjusted for each parameter are generated, and several first control strategies are obtained. Several first control strategies are simulated, second control strategies are determined based on the simulation results, and control instructions are issued.

[0014] The combustion safety control system and method of this application have the following advantages compared with the prior art: By collecting real-time key parameters and calculating real-time combustion evaluation values, it is determined whether control is needed based on the real-time combustion evaluation values. If so, several real-time control characteristics and corresponding parameters to be adjusted are determined. Combined with the control parameter-key parameter dependency model, several first control strategies are obtained. Control simulations are performed on several first control strategies to determine second control strategies and issue control instructions. The parameter status is accurately evaluated and reasonable control strategies are formulated to improve the efficiency of combustion safety control. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of a combustion safety control system according to an embodiment of this application; Figure 2 This is a schematic flowchart of a combustion safety control method according to an embodiment of this application. Detailed Implementation

[0016] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0017] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0020] like Figure 1 As shown in the figure, a combustion safety control system according to an embodiment of this application includes: The acquisition module is used to acquire, process, and analyze spectral data in real time to obtain real-time key parameters and calculate real-time combustion evaluation values ​​based on these parameters. The judgment module is used to determine whether control is needed based on the real-time combustion evaluation value. If so, it determines several real-time control features and the corresponding parameters that need to be adjusted. The generation module is used to generate the control parameters to be adjusted for each parameter based on the control parameter-key parameter dependency model, and to obtain several first control strategies; The control module is used to simulate the control of several first control strategies, determine the second control strategy based on the simulation results, and issue control instructions.

[0021] In this embodiment, a multispectral detector is used to collect real-time information on the combustion flame, obtain spectral data, and input it into the spectral analysis system. Through advanced spectral analysis technology, combined with a pre-established combustion model and spectral feature database, real-time key parameters are calculated. These real-time key parameters refer to core parameters such as flame temperature, ignition distance, and combustion stability.

[0022] In this embodiment, intelligent algorithms are used to process and analyze spectral data to achieve real-time measurement and reconstruction of the three-dimensional visualized temperature field of the entire furnace, obtaining real-time temperature field data that can intuitively display the temperature distribution at different locations within the furnace. A combustion condition simulation model is constructed based on combustion digital twin technology and real-time temperature field data, and control simulation is performed in conjunction with each first control strategy to obtain the simulation control effect of each first control strategy. The first control strategy with the best simulation control effect is set as the second control strategy.

[0023] In some embodiments of this application, calculating a real-time combustion evaluation value based on real-time key parameters includes: Several combustion evaluation indicators are preset, and each combustion evaluation indicator is mapped to several preset combustion characteristics; The correlation analysis was performed between several preset combustion characteristics of each combustion evaluation index and real-time key parameters to obtain the degree of correlation. Real-time key parameters with a correlation degree greater than a preset correlation degree threshold are set as correlation parameters of the corresponding preset combustion characteristics, and weight coefficients of the corresponding correlation parameters are set. Sequentially set the correlation parameters of several preset combustion characteristics for each combustion evaluation index; The associated parameters of each preset combustion feature are compared with the corresponding standard parameter range. If they are within the standard parameter range, the state coefficient of the corresponding key parameter is generated according to the first calculation formula. If they are not within the standard parameter range, the state coefficient of the corresponding key parameter is generated according to the second calculation formula. The first combustion evaluation coefficient corresponding to the preset combustion feature is generated based on the state coefficient of the associated parameters of the same preset combustion feature; The second combustion evaluation coefficient of the corresponding combustion evaluation index is generated based on the first combustion evaluation coefficient of several preset combustion characteristics of the same combustion evaluation index and the corresponding weight coefficient. Real-time combustion evaluation values ​​are generated based on the second combustion evaluation coefficients of several combustion evaluation indicators and their corresponding weighting coefficients.

[0024] In this embodiment, the first calculation formula is to calculate the critical parameter with the median of the corresponding standard parameter interval to obtain the anomaly probability of the critical parameter. That is, when the difference from the median is small, the corresponding anomaly probability is smaller and the state coefficient is larger, and vice versa. The second calculation formula is to calculate the critical parameter with the closest boundary value in the corresponding standard parameter interval to obtain the anomaly degree of the critical parameter. That is, when the difference from the boundary value is large, the corresponding anomaly degree is large and the state coefficient is smaller, and vice versa.

[0025] In this embodiment, the larger the state coefficient, the larger the first combustion evaluation coefficient, and vice versa. The larger the first combustion evaluation coefficient, the larger the corresponding second combustion evaluation coefficient, and vice versa. The larger the second combustion evaluation coefficient, the larger the corresponding real-time combustion evaluation value, and vice versa.

[0026] In this embodiment, by calculating the real-time combustion evaluation value, the presence of any abnormalities in the real-time combustion conditions is accurately assessed. If so, the corresponding optimization relationship and logic between each key combustion factor and control parameter are studied, thereby setting a reasonable combustion control strategy, improving combustion control efficiency, and effectively solving a series of practical problems such as boiler uneven combustion, local overheating of heating surfaces, high-temperature corrosion, ash accumulation, and high NOx content.

[0027] In some embodiments of this application, a determination is made based on the real-time combustion evaluation value to determine whether control is required. If so, several real-time control features and corresponding parameters to be adjusted are determined, including: Pre-set combustion evaluation thresholds; If the real-time combustion evaluation value is greater than the combustion evaluation value threshold, it is determined that no control is needed. If the real-time combustion evaluation value is not greater than the combustion evaluation value threshold, it is determined that control measures are needed. If control is required, select the combustion evaluation indicators to be optimized and set the number of control features for each combustion evaluation indicator to be optimized. Construct a sequence of undetermined control features for each combustion evaluation index to be optimized, and determine the real-time control features based on the number of control features; Set the number of adjustment parameters for each real-time control feature; Construct a sequence of undetermined adjustment parameters for each real-time control feature, and determine the parameters that need to be adjusted for the real-time control feature based on the number of adjustment parameters.

[0028] In some embodiments of this application, determining several real-time control features and corresponding parameters to be adjusted further includes: The preset second combustion evaluation coefficient threshold, the preset first combustion evaluation coefficient threshold, and the state coefficient threshold of each associated parameter are pre-set for each combustion evaluation index; Combustion evaluation indicators whose second combustion evaluation coefficient is less than the corresponding preset second combustion evaluation coefficient threshold are selected and set as combustion evaluation indicators to be optimized. Select the preset combustion features whose first combustion evaluation coefficient is less than the corresponding preset first combustion evaluation coefficient threshold in each combustion evaluation index to be optimized, and set them as features to be controlled. Construct a sequence of undetermined control features for each combustion evaluation index to be optimized, wherein the undetermined control features in the sequence are arranged according to their weight coefficients. The number of control features for each combustion evaluation indicator to be optimized is set according to the weight coefficient of each combustion evaluation indicator to be optimized and the difference between the corresponding second combustion evaluation value coefficients. Based on the number of control features, feature extraction is performed on the undetermined control feature sequence of the corresponding combustion evaluation index to be optimized, and real-time control features are determined based on the extraction results; The number of adjustment parameters for each real-time control feature is set according to the weight coefficient of each real-time control feature and the corresponding state coefficient difference. Based on the number of adjustment parameters, extract parameters from the sequence of undetermined adjustment parameters for the corresponding real-time control features, and determine the parameters to be adjusted for the real-time control features based on the extraction results.

[0029] In this embodiment, the larger the weight coefficient of the real-time control feature and the larger the difference in the state coefficient, the more adjustment parameters there are, and vice versa. The larger the difference between the weight coefficient of the combustion evaluation index to be optimized and the corresponding second combustion evaluation value coefficient, the more control features there are, and vice versa.

[0030] In this embodiment, by setting the number of control features and the number of adjustment parameters, the real-time control features and the sequence of parameters to be adjusted are extracted to obtain the real-time control features and the adjustment parameters of each real-time control feature. This clarifies the abnormal parameters affecting the current combustion conditions, lays the foundation for determining the optimization relationship and logic between key parameters and control parameters, and improves the effectiveness and efficiency of subsequent control strategies.

[0031] In some embodiments of this application, the control parameter-key parameter dependency model includes: Obtain historical control logs, extract the historical control node for each historical control parameter in each historical control log, and obtain the corresponding historical control quantity value; Set the historical monitoring period for each historical control parameter's historical control node; Obtain the historical change characteristics of each key parameter in the historical monitoring period of each historical control node, and generate historical change evaluation values; Key parameters whose historical change evaluation values ​​are greater than the preset change evaluation value threshold are set as undetermined dependent key parameters of the corresponding historical control parameters; Pre-set several control value ranges; Multiple historical control values ​​of the same historical control parameter from different historical control logs are assigned to the corresponding control value ranges. The first comparison is made of several undetermined key parameters corresponding to different historical control values ​​in the same control value range to obtain the frequency of occurrence of each undetermined key parameter. Remove undetermined dependent key parameters whose frequency of occurrence is less than a preset frequency threshold, and construct a control quantity value-change evaluation value matrix based on the historical change evaluation values ​​corresponding to the remaining undetermined dependent key parameters in different control quantity value ranges. Based on the control value-change evaluation value matrix, the historical control value sequence and the historical change evaluation value sequence of several undetermined critical coefficients are obtained. The dependence coefficient of each historical change evaluation value sequence on the historical control value sequence is calculated. Set the undetermined key parameters of the historical change evaluation value sequence with a dependency coefficient greater than the preset dependency coefficient threshold as the key parameters of the corresponding historical control parameters. Several dependent key parameters for each historical control parameter are generated sequentially; Construct a dependency key parameter-control parameter mapping table, where each dependency key parameter is mapped to several control parameters; Using each key parameter and its corresponding historical change features as training input data, and the control parameters mapped to each key parameter and their historical control values ​​as training output data, a neural network is trained to obtain a control parameter-key parameter dependency model.

[0032] In this embodiment, the historical attention period refers to the preset period after the corresponding historical control node, the historical control value refers to the adjustment value of the historical control parameter, and the historical change characteristics refer to the historical change value, the historical change rate, and the historical change trend. When the historical change value is larger, the historical change rate is faster, and the historical change trend is more volatile, the historical change evaluation value is larger, and vice versa.

[0033] In this embodiment, the frequency of occurrence refers to the ratio of the number of times the same pending dependent key parameter appears corresponding to different historical control values ​​within the same control value range to the total number of all historical control values ​​within the same control value range.

[0034] In this embodiment, the dependency coefficient refers to the time lag correlation between the historical change evaluation value sequence and the historical control value sequence. That is, the historical change evaluation value sequence of the corresponding key parameter changes with the changes in the historical control value sequence. The greater the change with the changes in the historical control value, the greater the corresponding dependency coefficient, and vice versa.

[0035] In this embodiment, a control parameter-key parameter dependency model is constructed to lay the foundation for determining the controllable parameters for each parameter that needs to be regulated, thereby improving the efficiency of combustion safety management.

[0036] In some embodiments of this application, before generating the control parameters to be adjusted for each parameter based on the control parameter-key parameter dependency model and obtaining several first control strategies, the process includes: The number of first combustion evaluation coefficients to be optimized for each control feature is determined based on the difference in the second combustion evaluation coefficients for each evaluation indicator to be optimized, the number of corresponding control features, and the weight coefficients corresponding to the control features. The number of state systems to be optimized for each control feature is determined based on the number of first combustion evaluation systems to be optimized for each control feature, the number of corresponding adjustment parameters, and the weight coefficients corresponding to the parameters to be adjusted. The required adjustment value for each parameter is determined based on the quantity of the state system to be optimized for each parameter.

[0037] In this embodiment, the quantity value of the first combustion evaluation coefficient to be optimized is the amount of the first combustion evaluation coefficient to be adjusted based on the second combustion evaluation difference of the evaluation index to be optimized and allocated to each control feature. When the number of control features is smaller and the weight coefficient corresponding to the control feature is larger, the quantity value of the first combustion evaluation coefficient to be optimized for the corresponding control feature is larger. After adjustment according to the quantity value of the first combustion evaluation coefficient to be optimized, the second combustion evaluation coefficient of the corresponding evaluation index to be optimized is greater than the preset second combustion evaluation coefficient threshold.

[0038] In this embodiment, the number of optimization champion systems refers to the amount of state coefficient to be adjusted at each parameter to be adjusted, which is allocated to the number of optimization first combustion evaluation systems of each control feature. When the number of adjustment parameters is smaller and the weight coefficient corresponding to the parameter to be adjusted is larger, the number of optimization state systems of the corresponding parameter to be adjusted is larger.

[0039] In this embodiment, by determining the adjustment value of each parameter that needs to be adjusted, a foundation is laid for subsequently determining the controllable parameters that need to be adjusted, thereby improving the accuracy of setting the controllable parameters and improving the efficiency of combustion control.

[0040] In some embodiments of this application, the control parameters to be controlled for each parameter that needs adjustment are generated based on a control parameter-key parameter dependency model, resulting in several first control strategies, including: Each parameter that needs adjustment and its corresponding adjustment value are input into the control parameter-key parameter dependency model to obtain several parameters to be controlled for each parameter that needs adjustment and the control value of each parameter to be controlled. Randomly select each parameter to be adjusted as the target parameter to be controlled; Construct a first control strategy based on all target parameters that need to be adjusted; Several primary control strategies are generated.

[0041] In some embodiments of this application, control simulation is performed on several first control strategies, including: Intelligent algorithms are used to process and analyze spectral data to obtain real-time temperature field data; It can intuitively display the temperature distribution at different locations inside the furnace, and construct a combustion condition simulation model based on combustion digital twin technology and real-time temperature field data; Based on the combustion condition simulation model, control simulations were performed for each first control strategy, and simulation results for each first control strategy were obtained. The simulation results include simulated change characteristics of several parameters that need to be adjusted.

[0042] In some embodiments of this application, a second control strategy is determined based on simulation results, and control instructions are issued, including: Calculate the simulation state coefficient of the corresponding parameter to be adjusted based on the simulation change value in the simulation change characteristics of each parameter to be adjusted; The simulation compensation coefficients are generated based on the simulated rate of change and the simulated trend of change in the simulated change characteristics. The simulated first combustion evaluation coefficient for the corresponding control characteristics is calculated based on the simulated state coefficient, the simulated compensation coefficient, and the weight coefficients of the corresponding parameters to be adjusted. Based on the simulated first combustion evaluation coefficient of several control features of the same combustion evaluation index to be optimized and the weight coefficient of the corresponding control features, a simulated second combustion evaluation coefficient of the corresponding combustion evaluation index to be optimized is generated. The simulated combustion evaluation value is generated based on the simulated second combustion evaluation coefficients of several combustion evaluation indicators to be optimized, the weight coefficients of the corresponding combustion evaluation indicators to be optimized, and the second combustion evaluation coefficients of other combustion evaluation indicators. The simulated combustion evaluation values ​​of all the first control strategies are sorted, the second control strategy is determined based on the sorting results, and control instructions are issued according to the second control strategy.

[0043] In this embodiment, the simulated combustion evaluation values ​​of all first control strategies are sorted from largest to smallest, and the first control strategy corresponding to the simulated combustion evaluation value ranked first is set as the second control strategy.

[0044] In this embodiment, the compensation coefficient is set according to the simulated change trend and the simulated change rate. The greater the fluctuation of the simulated change trend and the faster the simulated change rate, the smaller the compensation coefficient, which means that the parameter to be adjusted is more unstable. Conversely, the compensation coefficient is larger. The range of the compensation coefficient is (0.85, 1.15).

[0045] In this embodiment, the control effect of each first control strategy is evaluated by calculating simulated combustion evaluation values, thereby determining the second control strategy, i.e. the optimal control strategy, and improving the efficiency of combustion safety control.

[0046] In some embodiments of this application, such as Figure 2 As shown, it also includes a combustion safety management method: Step S201: Collect spectral data in real time, process and analyze it to obtain real-time key parameters, and calculate the real-time combustion evaluation value based on the real-time key parameters; Step S202: Determine whether control is needed based on the real-time combustion evaluation value. If so, determine several real-time control features and the corresponding parameters that need to be adjusted. Step S203: Generate the control parameters to be adjusted for each parameter based on the control parameter-key parameter dependency model, and obtain several first control strategies; Step S204: Perform control simulation on several first control strategies, determine the second control strategy based on the simulation results, and issue control instructions.

[0047] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.

Claims

1. A combustion safety control system, characterized in that, include: The acquisition module is used to acquire, process, and analyze spectral data in real time to obtain real-time key parameters and calculate real-time combustion evaluation values ​​based on these parameters. The judgment module is used to determine whether control is needed based on the real-time combustion evaluation value. If so, it determines several real-time control features and the corresponding parameters that need to be adjusted. The generation module is used to generate the control parameters to be adjusted for each parameter based on the control parameter-key parameter dependency model, and to obtain several first control strategies. The control module is used to simulate the control of several first control strategies, determine the second control strategy based on the simulation results, and issue control instructions.

2. The combustion safety control system as described in claim 1, characterized in that, Real-time combustion evaluation values ​​are calculated based on real-time key parameters, including: Several combustion evaluation indicators are preset, and each combustion evaluation indicator is mapped to several preset combustion characteristics; The correlation analysis was performed between several preset combustion characteristics of each combustion evaluation index and real-time key parameters to obtain the degree of correlation. Real-time key parameters with a correlation degree greater than a preset correlation degree threshold are set as correlation parameters of the corresponding preset combustion characteristics, and weight coefficients of the corresponding correlation parameters are set. Sequentially set the correlation parameters of several preset combustion characteristics for each combustion evaluation index; The associated parameters of each preset combustion feature are compared with the corresponding standard parameter range. If they are within the standard parameter range, the state coefficient of the corresponding key parameter is generated according to the first calculation formula. If they are not within the standard parameter range, the state coefficient of the corresponding key parameter is generated according to the second calculation formula. The first combustion evaluation coefficient corresponding to the preset combustion feature is generated based on the state coefficient of the associated parameters of the same preset combustion feature; The second combustion evaluation coefficient of the corresponding combustion evaluation index is generated based on the first combustion evaluation coefficient of several preset combustion characteristics of the same combustion evaluation index and the corresponding weight coefficient. Real-time combustion evaluation values ​​are generated based on the second combustion evaluation coefficients of several combustion evaluation indicators and their corresponding weighting coefficients.

3. The combustion safety control system as described in claim 2, characterized in that, Determine whether control is needed based on real-time combustion evaluation values. If so, identify several real-time control characteristics and corresponding parameters that need adjustment, including: Pre-set combustion evaluation thresholds; If the real-time combustion evaluation value is greater than the combustion evaluation value threshold, it is determined that no control is needed. If the real-time combustion evaluation value is not greater than the combustion evaluation value threshold, it is determined that control measures are needed. If control is required, select the combustion evaluation indicators to be optimized and set the number of control features for each combustion evaluation indicator to be optimized. Construct a sequence of undetermined control features for each combustion evaluation index to be optimized, and determine the real-time control features based on the number of control features; Set the number of adjustment parameters for each real-time control feature; Construct a sequence of undetermined adjustment parameters for each real-time control feature, and determine the parameters that need to be adjusted for the real-time control feature based on the number of adjustment parameters.

4. The combustion safety control system as described in claim 3, characterized in that, The determination of several real-time control characteristics and corresponding parameters that need to be adjusted also includes: The preset second combustion evaluation coefficient threshold, the preset first combustion evaluation coefficient threshold, and the state coefficient threshold of each associated parameter are pre-set for each combustion evaluation index; Combustion evaluation indicators whose second combustion evaluation coefficient is less than the corresponding preset second combustion evaluation coefficient threshold are selected and set as combustion evaluation indicators to be optimized. Select the preset combustion features whose first combustion evaluation coefficient is less than the corresponding preset first combustion evaluation coefficient threshold in each combustion evaluation index to be optimized, and set them as features to be controlled. Construct a sequence of undetermined control features for each combustion evaluation index to be optimized, wherein the undetermined control features in the sequence are arranged according to their weight coefficients. The number of control features for each combustion evaluation indicator to be optimized is set according to the weight coefficient of each combustion evaluation indicator to be optimized and the difference between the corresponding second combustion evaluation value coefficients. Based on the number of control features, feature extraction is performed on the undetermined control feature sequence of the corresponding combustion evaluation index to be optimized, and real-time control features are determined based on the extraction results; The number of adjustment parameters for each real-time control feature is set according to the weight coefficient of each real-time control feature and the corresponding state coefficient difference. Based on the number of adjustment parameters, extract parameters from the sequence of undetermined adjustment parameters for the corresponding real-time control features, and determine the parameters to be adjusted for the real-time control features based on the extraction results.

5. The combustion safety control system as described in claim 1, characterized in that, The control parameter-key parameter dependency model includes: Obtain historical control logs, extract the historical control node for each historical control parameter in each historical control log, and obtain the corresponding historical control quantity value; Set the historical monitoring period for each historical control parameter's historical control node; Obtain the historical change characteristics of each key parameter in the historical monitoring period of each historical control node, and generate historical change evaluation values; Key parameters whose historical change evaluation values ​​are greater than the preset change evaluation value threshold are set as undetermined dependent key parameters of the corresponding historical control parameters; Pre-set several control value ranges; Multiple historical control values ​​of the same historical control parameter from different historical control logs are assigned to the corresponding control value ranges. The first comparison is made of several undetermined key parameters corresponding to different historical control values ​​in the same control value range to obtain the frequency of occurrence of each undetermined key parameter. Remove undetermined dependent key parameters whose frequency of occurrence is less than a preset frequency threshold, and construct a control quantity value-change evaluation value matrix based on the historical change evaluation values ​​corresponding to the remaining undetermined dependent key parameters in different control quantity value ranges. Based on the control value-change evaluation value matrix, the historical control value sequence and the historical change evaluation value sequence of several undetermined critical coefficients are obtained. The dependence coefficient of each historical change evaluation value sequence on the historical control value sequence is calculated. Set the undetermined key parameters of the historical change evaluation value sequence with a dependency coefficient greater than the preset dependency coefficient threshold as the key parameters of the corresponding historical control parameters. Several dependent key parameters for each historical control parameter are generated sequentially; Construct a dependency key parameter-control parameter mapping table, where each dependency key parameter is mapped to several control parameters; Using each key parameter and its corresponding historical change features as training input data, and the control parameters mapped to each key parameter and their historical control values ​​as training output data, a neural network is trained to obtain a control parameter-key parameter dependency model.

6. The combustion safety control system as described in claim 5, characterized in that, Based on the control parameter-key parameter dependency model, each parameter to be adjusted is generated as a control parameter, and several first control strategies are obtained beforehand, including: The number of first combustion evaluation coefficients to be optimized for each control feature is determined based on the difference in the second combustion evaluation coefficients for each evaluation indicator to be optimized, the number of corresponding control features, and the weight coefficients corresponding to the control features. The number of state systems to be optimized for each control feature is determined based on the number of first combustion evaluation systems to be optimized for each control feature, the number of corresponding adjustment parameters, and the weight coefficients corresponding to the parameters to be adjusted. The required adjustment value for each parameter is determined based on the quantity of the state system to be optimized for each parameter.

7. The combustion safety control system as described in claim 6, characterized in that, Based on the control parameter-key parameter dependency model, the control parameters to be adjusted for each parameter are generated, and several first control strategies are obtained, including: Each parameter that needs adjustment and its corresponding adjustment value are input into the control parameter-key parameter dependency model to obtain several parameters to be controlled for each parameter that needs adjustment and the control value of each parameter to be controlled. Randomly select each parameter to be adjusted as the target parameter to be controlled; Construct a first control strategy based on all target parameters that need to be adjusted; Several primary control strategies are generated.

8. The combustion safety control system as described in claim 7, characterized in that, Control simulations were conducted for several primary control strategies, including: Intelligent algorithms are used to process and analyze spectral data to obtain real-time temperature field data; It can intuitively display the temperature distribution at different locations inside the furnace, and construct a combustion condition simulation model based on combustion digital twin technology and real-time temperature field data; Based on the combustion condition simulation model, control simulations were performed for each first control strategy, and simulation results for each first control strategy were obtained. The simulation results include simulated change characteristics of several parameters that need to be adjusted.

9. The combustion safety control system as described in claim 8, characterized in that, Based on the simulation results, a second control strategy is determined, and control instructions are issued, including: Calculate the simulation state coefficient of the corresponding parameter to be adjusted based on the simulation change value in the simulation change characteristics of each parameter to be adjusted; The simulation compensation coefficients are generated based on the simulated rate of change and the simulated trend of change in the simulated change characteristics. The simulated first combustion evaluation coefficient for the corresponding control characteristics is calculated based on the simulated state coefficient, the simulated compensation coefficient, and the weight coefficients of the corresponding parameters to be adjusted. Based on the simulated first combustion evaluation coefficient of several control features of the same combustion evaluation index to be optimized and the weight coefficient of the corresponding control features, a simulated second combustion evaluation coefficient of the corresponding combustion evaluation index to be optimized is generated. The simulated combustion evaluation value is generated based on the simulated second combustion evaluation coefficients of several combustion evaluation indicators to be optimized, the weight coefficients of the corresponding combustion evaluation indicators to be optimized, and the second combustion evaluation coefficients of other combustion evaluation indicators. The simulated combustion evaluation values ​​of all the first control strategies are sorted, the second control strategy is determined based on the sorting results, and control instructions are issued according to the second control strategy.

10. A method for controlling combustion safety, characterized in that, include: Real-time acquisition, processing, and analysis of spectral data are used to obtain real-time key parameters, and real-time combustion evaluation values ​​are calculated based on these parameters. Determine whether control is needed based on real-time combustion evaluation values. If so, identify several real-time control features and corresponding parameters that need to be adjusted. Based on the control parameter-key parameter dependency model, the control parameters to be adjusted for each parameter are generated, and several first control strategies are obtained. Several first control strategies are simulated, second control strategies are determined based on the simulation results, and control instructions are issued.

Images