Combustor optimized combustion control method and system

Abstract

The invention discloses an optimized combustion control method and system for a combustor, and the method comprises the steps: obtaining a real-time combustion state parameter, and evaluating the real-time combustion state parameter based on a plurality of combustion evaluation indexes to obtain a real-time combustion evaluation value; when the real-time combustion evaluation value is smaller than the standard combustion evaluation value, a preset control model is determined according to the combustion evaluation value difference in combination with the real-time operation working condition, and an initial control method of the combustor is obtained; performing control simulation based on an initial control method to obtain simulation change characteristics of each real-time combustion state parameter, and optimizing corresponding control parameters in the initial control method according to the simulation change characteristics to obtain an optimized control method; by continuously optimizing and adjusting the control parameters of the combustor, the control efficiency and control precision of the combustor are improved, and efficient and stable operation of the combustor is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of burners, and in particular to a burner optimization combustion control method and system. Background Art

[0002] Fine control of boiler burners is of great significance to the safe and stable operation of boilers. It can not only effectively prevent abnormal combustion behavior, but also improve the combustion efficiency and combustion utilization rate of the boiler, so that the boiler can operate safely, reliably and stably. Therefore, it is necessary to judge the combustion state of the burner at all times and perform optimal control when the burner is running. Therefore, in order to achieve accurate judgment of the combustion state of the burner and improve the optimization control effect, a burner optimization combustion control method and system are urgently needed. Summary of the invention

[0003] To solve the above technical problems, the present application provides a burner optimization combustion control method and system, which calculates the real-time combustion evaluation value to obtain the combustion evaluation value difference, and determines the preset control model in combination with the real-time operating conditions, obtains the initial control method according to the preset control model, simulates the initial control method, obtains the simulated change characteristics of each real-time combustion state parameter and calculates the state coefficient, optimizes the control parameters associated with the real-time combustion state parameters in the initial control method according to the state coefficient, and obtains the optimized control method, and improves the control efficiency and control accuracy of the burner by continuously optimizing and adjusting the control parameters of the burner, thereby achieving safe, efficient and stable operation of the burner.

[0004] In some embodiments of the present application, a burner optimization combustion control method is provided, comprising:

[0005] Acquire real-time combustion state parameters, evaluate the real-time combustion state parameters based on multiple combustion evaluation indicators, and obtain a real-time combustion evaluation value;

[0006] When the real-time combustion evaluation value is less than the standard combustion evaluation value, the preset control model is determined according to the difference in the combustion evaluation values ​​combined with the real-time operating conditions, and the initial control method of the burner is obtained;

[0007] A control simulation is performed based on the initial control method to obtain the simulated change characteristics of each real-time combustion state parameter. The corresponding control parameters in the initial control method are optimized according to the simulated change characteristics to obtain an optimized control method. The control instructions of the burner are generated according to the optimized control method.

[0008] In some embodiments of the present application, the real-time combustion state parameters are evaluated based on multiple combustion evaluation indicators to obtain a real-time combustion evaluation value, including:

[0009] Pre-set multiple combustion evaluation indicators;

[0010] Determining the real-time combustion state parameter associated with each combustion evaluation index according to the degree of association between the real-time combustion state parameter and the combustion evaluation index;

[0011] Comparing the real-time combustion state parameter associated with each combustion evaluation index with the corresponding standard combustion state parameter to obtain a plurality of real-time combustion state parameter difference values, and generating a sub-evaluation value of the corresponding combustion evaluation index;

[0012] A real-time combustion evaluation value is generated according to the sub-evaluation values ​​of the plurality of combustion evaluation indicators and the corresponding weight coefficients.

[0013] In some embodiments of the present application, when the real-time combustion evaluation value is less than the standard combustion evaluation value, a preset control model is determined according to the difference in the combustion evaluation value combined with the real-time operating conditions, including:

[0014] When the real-time combustion evaluation value is less than the standard combustion evaluation value, the combustion evaluation value difference is calculated and the real-time operating condition of the current burner is obtained;

[0015] Perform similarity analysis on the real-time operating conditions and the historical operating conditions in the operating condition record table to obtain comprehensive similarity;

[0016] Obtain a historical control reference library of historical operating conditions with the greatest comprehensive similarity to the real-time operating conditions, and build a preset control model based on the current historical control reference library;

[0017] The historical control reference library includes a plurality of preset combustion evaluation value differences, and each preset combustion evaluation value difference is associated with a specific preset control method.

[0018] In some embodiments of the present application, a method for obtaining an initial control of a burner includes:

[0019] Based on several preset combustion evaluation value differences in the current historical control reference library as training input data and corresponding preset control methods as training output data, neural network training is performed to obtain a preset control model;

[0020] Inputting the combustion evaluation value difference into a preset control model to obtain a plurality of first control methods;

[0021] Compare the multiple control parameters in the first control method with the corresponding real-time control parameters respectively and predict the predicted control time, predicted control cost and predicted control stability of the corresponding control parameters;

[0022] Generate a prediction control evaluation value corresponding to the first control method according to the prediction control duration, the prediction control cost and the prediction control stability;

[0023] The first control method having the largest predictive control evaluation value is set as the initial control method.

[0024] In some embodiments of the present application, a similarity analysis is performed between the real-time operating condition and the historical operating condition in the operating condition record table to obtain a comprehensive similarity, including:

[0025] Preset multiple working condition evaluation indicators, and generate historical comprehensive working condition evaluation values ​​of multiple working condition evaluation indicators based on historical operating conditions;

[0026] Based on each historical operating condition parameter in the historical operating condition as the horizontal coordinate and the historical comprehensive operating condition evaluation value as the vertical coordinate, the operating condition relationship curve under different preset time lengths is constructed;

[0027] Comparing the correlation of the same historical operating condition parameter under different preset durations according to multiple operating condition relationship curves, and setting the preset duration with the greatest correlation as the target duration corresponding to the historical operating condition parameter;

[0028] The target durations of multiple historical working conditions are averaged to obtain the standard duration;

[0029] Taking the standard time length as the time reference line, setting multiple collection nodes at preset time intervals, obtaining multiple real-time operating condition parameters of the real-time operating condition and multiple historical operating condition parameters of the historical operating condition according to the collection nodes, and mapping them to the time reference line to generate a working condition parameter comparison reference diagram;

[0030] Calculate the difference between each real-time operating condition parameter and the corresponding historical operating condition parameter in the operating condition parameter comparison reference diagram at each acquisition node, and generate a difference similarity based on multiple operating condition parameter differences at multiple acquisition nodes;

[0031] Calculate the fluctuation value difference of each real-time operating condition parameter of the real-time operating condition in the operating condition comparison reference diagram and the historical operating condition parameter corresponding to the historical operating condition at each acquisition node, and generate fluctuation similarity according to multiple fluctuation value differences at multiple acquisition nodes;

[0032] Generate comprehensive similarity based on difference similarity and fluctuation similarity.

[0033] In some embodiments of the present application, generating a comprehensive similarity based on the difference similarity and the fluctuation similarity includes:

[0034] The calculation formula of the comprehensive similarity is:

[0035]

[0036] Among them, H is the comprehensive similarity, g1 is the weight coefficient of difference similarity, y1i,z is the i-th real-time operating condition parameter at the z-th acquisition node, △yi,z is the difference of the i-th operating condition parameter at the z-th acquisition node, n is the total number of real-time operating condition parameters of real-time operation conditions, m is the total number of acquisition nodes, △wi,z is the i-th fluctuation value difference at the z-th acquisition node, and g2 is the weight coefficient of fluctuation similarity.

[0037] In some embodiments of the present application, a control simulation is performed based on the initial control method to obtain a simulated change feature of each real-time combustion state parameter, including:

[0038] Performing a control simulation of the burner based on the initial control method to obtain a control simulation result, wherein the control simulation result includes a plurality of simulated combustion state parameters after the initial control method;

[0039] By comparing the simulated combustion state parameters with the corresponding real-time combustion state parameters, the simulated change value, simulated change trend and simulated change stability of each real-time combustion state parameter within the control simulation time of the initial control method are obtained;

[0040] The simulated change value, simulated change trend and simulated change stability of each real-time combustion state parameter are set as the first simulated change feature corresponding to the real-time combustion state parameter;

[0041] generating a simulated sub-evaluation value of the corresponding combustion evaluation index according to the simulated combustion state parameter associated with the corresponding combustion evaluation index, and setting a difference between the simulated sub-evaluation value and the first evaluation value of the sub-evaluation value as a second simulated change characteristic of the real-time combustion state parameter associated with the corresponding combustion evaluation index;

[0042] generating a simulated combustion evaluation value according to the plurality of simulated sub-evaluation values, and setting a simulated compensation coefficient according to a difference between the simulated combustion evaluation value and a second evaluation value of the real-time combustion evaluation value;

[0043] Generate a state coefficient corresponding to the real-time combustion state parameter according to the first simulated change characteristic, the second simulated change characteristic and the simulated compensation coefficient;

[0044] The calculation formula of the state coefficient is:

[0045]

[0046] Among them, U is the state coefficient, r is the simulation compensation coefficient, c1 is the first state conversion coefficient, v1 is the weight coefficient of the first simulation change feature, B is the simulation change value, K is the simulation change stability, p is the simulation change trend, when the simulation change trend is a normal trend, p=1, when the simulation change trend is an abnormal trend, p=-1, c2 is the second state conversion coefficient, v2 is the weight coefficient of the second simulation change feature, s is the total number of combustion evaluation indicators associated with the current real-time combustion state parameter, L1x is the simulation sub-evaluation value of the xth combustion evaluation indicator associated with the current simulated combustion state parameter, L0x is the sub-evaluation value of the xth combustion evaluation indicator associated with the real-time combustion state parameter corresponding to the current simulated combustion state parameter, and L1x-L0x is the first evaluation value difference of the xth combustion evaluation indicator.

[0047] In some embodiments of the present application, the corresponding control parameters in the initial control method are optimized according to the simulated change characteristics, including:

[0048] Screen out the real-time combustion state parameters whose state coefficients are less than a preset state coefficient threshold value, and set them as the state parameters to be optimized;

[0049] Obtaining a historical control log of the state parameter to be optimized, and determining a control parameter associated with each state parameter to be optimized according to the degree of synchronous change between the historical control parameters involved in the historical control log and the state parameter to be optimized;

[0050] Determining the control parameters to be optimized in the initial control method according to the control parameters associated with each state parameter to be optimized;

[0051] The correction coefficient of the control parameter to be optimized in the initial control method is determined according to the state coefficient difference between each state parameter to be optimized and a preset state coefficient threshold.

[0052] In some embodiments of the present application, an optimization control method is obtained, including:

[0053] The control parameters to be optimized in the initial control method are corrected based on the correction coefficient to obtain the optimized control parameters;

[0054] The optimized control parameters are used to replace the corresponding control parameters in the initial control method to obtain the optimized control method.

[0055] In some embodiments of the present application, a burner optimization combustion control system is also included:

[0056] An acquisition module is used to acquire real-time combustion state parameters, evaluate the real-time combustion state parameters based on multiple combustion evaluation indicators, and obtain a real-time combustion evaluation value;

[0057] A determination module, used to determine a preset control model according to the difference in the combustion evaluation values ​​combined with the real-time operating conditions when the real-time combustion evaluation value is less than the standard combustion evaluation value, and obtain an initial control method for the burner;

[0058] The control module is used to perform control simulation based on the initial control method to obtain the simulated change characteristics of each real-time combustion state parameter, optimize the corresponding control parameters in the initial control method according to the simulated change characteristics, obtain the optimized control method, and generate the control instructions of the burner according to the optimized control method.

[0059] Compared with the prior art, the burner optimization combustion control method and system of the embodiment of the present application have the following beneficial effects:

[0060] By calculating the real-time combustion evaluation value, the combustion evaluation value difference is obtained, and the preset control model is determined in combination with the real-time operating conditions. The initial control method is obtained according to the preset control model, and the initial control method is simulated to obtain the simulated change characteristics of each real-time combustion state parameter and calculate the state coefficient. The control parameters associated with the real-time combustion state parameters in the initial control method are optimized according to the state coefficient to obtain the optimized control method. By continuously optimizing and adjusting the control parameters of the burner, the control efficiency and control accuracy of the burner are improved, and the safe, efficient and stable operation of the burner is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a burner optimization combustion control method in a preferred embodiment of the present application;

[0062] Figure 2 It is a schematic diagram of a burner optimization combustion control system in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0063] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0064] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0065] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0066] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0067] like Figure 1 As shown, a burner optimization combustion control method according to a preferred embodiment of the present application includes:

[0068] Acquire real-time combustion state parameters, evaluate the real-time combustion state parameters based on multiple combustion evaluation indicators, and obtain a real-time combustion evaluation value;

[0069] When the real-time combustion evaluation value is less than the standard combustion evaluation value, the preset control model is determined according to the difference in the combustion evaluation values ​​combined with the real-time operating conditions, and the initial control method of the burner is obtained;

[0070] A control simulation is performed based on the initial control method to obtain the simulated change characteristics of each real-time combustion state parameter. The corresponding control parameters in the initial control method are optimized according to the simulated change characteristics to obtain an optimized control method. The control instructions of the burner are generated according to the optimized control method.

[0071] In this embodiment, the real-time combustion state parameters refer to the parameters that can currently represent the operating state, stable state, efficiency state, etc. of the burner, for example, nitrogen oxide content, furnace temperature and pressure, air ratio, etc. The combustion evaluation index includes a combustion stability evaluation index, a combustion safety evaluation index, a combustion efficiency evaluation index, a combustion energy consumption evaluation index, and a combustion cost evaluation index. The real-time combustion evaluation value refers to the comprehensive evaluation result of multiple combustion evaluation indicators. The standard combustion evaluation value refers to the comprehensive evaluation value of multiple combustion evaluation indicators to ensure the normal operation of the burner.

[0072] In this embodiment, the preset control model is constructed in advance based on the historical combustion evaluation value differences of different historical operating conditions and the corresponding historical control methods. The simulation change characteristics refer to the change values, fluctuation values ​​and change trends of the real-time combustion state parameters before and after the control simulation of the initial control method.

[0073] In this embodiment, by calculating the real-time combustion evaluation value of the burner, the corresponding preset control model is screened out according to the real-time combustion evaluation value and the real-time operating conditions, and the corresponding initial control method is obtained. The initial control method is simulated to obtain the simulated change characteristics of each real-time combustion state parameter. The initial control method is optimized according to the simulated change characteristics to obtain an optimized control method, thereby realizing continuous optimization of the control parameters of the burner and ensuring the safe and stable operation of the burner.

[0074] In some embodiments of the present application, the real-time combustion state parameters are evaluated based on multiple combustion evaluation indicators to obtain a real-time combustion evaluation value, including:

[0075] Pre-set multiple combustion evaluation indicators;

[0076] Determining the real-time combustion state parameter associated with each combustion evaluation index according to the degree of association between the real-time combustion state parameter and the combustion evaluation index;

[0077] Comparing the real-time combustion state parameter associated with each combustion evaluation index with the corresponding standard combustion state parameter to obtain a plurality of real-time combustion state parameter difference values, and generating a sub-evaluation value of the corresponding combustion evaluation index;

[0078] A real-time combustion evaluation value is generated according to the sub-evaluation values ​​of the plurality of combustion evaluation indicators and the corresponding weight coefficients.

[0079] In this embodiment, the degree of correlation between the real-time combustion state parameters and the combustion evaluation index is judged based on the application frequency of the parameters and the importance of the parameters in the historical evaluation process of the combustion evaluation index. When the application frequency of the real-time combustion state parameters in evaluating the combustion evaluation index is greater than the preset application frequency and the parameter importance is greater than the preset importance threshold, the degree of correlation is greater than the preset degree of correlation, that is, the real-time combustion state parameters are associated with the corresponding combustion evaluation index.

[0080] In this embodiment, the standard combustion state parameter refers to the minimum combustion state parameter that meets the requirements of the corresponding combustion evaluation index, which is set in advance based on the historical parameters. When the difference between the real-time combustion state parameters is larger, the sub-evaluation value of the corresponding combustion evaluation index is smaller, and vice versa.

[0081] In this embodiment, the sub-evaluation values ​​of multiple combustion evaluation indicators are calculated to obtain a real-time combustion evaluation value, and it is determined whether regulation is needed. If necessary, the corresponding initial control method is determined, and the initial control method is continuously optimized to achieve optimized operation of the burner and improve the control efficiency and control accuracy of the burner.

[0082] In some embodiments of the present application, when the real-time combustion evaluation value is less than the standard combustion evaluation value, a preset control model is determined according to the difference in the combustion evaluation value combined with the real-time operating conditions, including:

[0083] When the real-time combustion evaluation value is less than the standard combustion evaluation value, the combustion evaluation value difference is calculated and the real-time operating condition of the current burner is obtained;

[0084] Perform similarity analysis on the real-time operating conditions and the historical operating conditions in the operating condition record table to obtain comprehensive similarity;

[0085] Obtain a historical control reference library of historical operating conditions with the greatest comprehensive similarity to the real-time operating conditions, and build a preset control model based on the current historical control reference library;

[0086] The historical control reference library includes a plurality of preset combustion evaluation value differences, and each preset combustion evaluation value difference is associated with a specific preset control method.

[0087] In this embodiment, the specific preset control method refers to a historical control method in which the historical combustion evaluation value after adjustment is greater than the standard combustion evaluation value.

[0088] In this embodiment, the operating condition record table includes multiple operating conditions and a historical control reference library of corresponding operating conditions. By comparing the real-time operating conditions with the historical operating conditions, a comprehensive similarity is obtained, and the historical operating conditions with the greatest similarity and the corresponding historical control reference library are screened out, laying the foundation for the subsequent determination of the initial control method, improving the control efficiency and control efficiency of the current burner, and ensuring the optimized operation of the burner.

[0089] In some embodiments of the present application, a method for obtaining an initial control of a burner includes:

[0090] Based on several preset combustion evaluation value differences in the current historical control reference library as training input data and corresponding preset control methods as training output data, neural network training is performed to obtain a preset control model;

[0091] Inputting the combustion evaluation value difference into a preset control model to obtain a plurality of first control methods;

[0092] Compare the multiple control parameters in the first control method with the corresponding real-time control parameters respectively and predict the predicted control time, predicted control cost and predicted control stability of the corresponding control parameters;

[0093] Generate a prediction control evaluation value corresponding to the first control method according to the prediction control duration, the prediction control cost and the prediction control stability;

[0094] The first control method having the largest predictive control evaluation value is set as the initial control method.

[0095] In this embodiment, predictive control stability refers to whether the burner operates stably within the predictive control time. When the predictive control time is short, the predictive control cost is low, and the predictive control stability is strong, the larger the predictive control evaluation value is, the multiple first control methods are sorted according to the predictive control evaluation value, and the first control method ranked first is set as the initial control method to improve the combustion stability of the burner and reduce the control cost.

[0096] In some embodiments of the present application, a similarity analysis is performed between the real-time operating condition and the historical operating condition in the operating condition record table to obtain a comprehensive similarity, including:

[0097] Preset multiple working condition evaluation indicators, and generate historical comprehensive working condition evaluation values ​​of multiple working condition evaluation indicators based on historical operating conditions;

[0098] Based on each historical operating condition parameter in the historical operating condition as the horizontal coordinate and the historical comprehensive operating condition evaluation value as the vertical coordinate, the operating condition relationship curve under different preset time lengths is constructed;

[0099] Comparing the correlation of the same historical operating condition parameter under different preset durations according to multiple operating condition relationship curves, and setting the preset duration with the greatest correlation as the target duration corresponding to the historical operating condition parameter;

[0100] The target durations of multiple historical working conditions are averaged to obtain the standard duration;

[0101] Taking the standard time length as the time reference line, setting multiple collection nodes at preset time intervals, obtaining multiple real-time operating condition parameters of the real-time operating condition and multiple historical operating condition parameters of the historical operating condition according to the collection nodes, and mapping them to the time reference line to generate a working condition parameter comparison reference diagram;

[0102] Calculate the difference between each real-time operating condition parameter and the corresponding historical operating condition parameter in the operating condition parameter comparison reference diagram at each acquisition node, and generate a difference similarity based on multiple operating condition parameter differences at multiple acquisition nodes;

[0103] Calculate the fluctuation value difference of each real-time operating condition parameter of the real-time operating condition in the operating condition comparison reference diagram and the historical operating condition parameter corresponding to the historical operating condition at each acquisition node, and generate fluctuation similarity according to multiple fluctuation value differences at multiple acquisition nodes;

[0104] Generate comprehensive similarity based on difference similarity and fluctuation similarity.

[0105] In this embodiment, the operating condition evaluation indicators include operating condition safety, operating condition stability, etc., and the degree of correlation includes linear correlation and nonlinear correlation. The change relationship of different historical operating condition parameters for different preset time lengths is determined, and the target time length of each historical operating condition parameter is screened out, and the mean processing is performed to obtain the standard time length, thereby reducing the impact of the extended error caused by the data processing of the operating condition parameters, facilitating subsequent parameter processing and similarity analysis, and improving the similarity accuracy between the real-time operating condition and the historical operating condition, laying the foundation for the subsequent determination of the initial control method.

[0106] In some embodiments of the present application, generating a comprehensive similarity based on the difference similarity and the fluctuation similarity includes:

[0107] The calculation formula of the comprehensive similarity is:

[0108]

[0110] Among them, H is the comprehensive similarity, g1 is the weight coefficient of difference similarity, y1i,z is the i-th real-time operating condition parameter at the z-th acquisition node, △yi,z is the difference of the i-th operating condition parameter at the z-th acquisition node, n is the total number of real-time operating condition parameters of real-time operation conditions, m is the total number of acquisition nodes, △wi,z is the i-th fluctuation value difference at the z-th acquisition node, and g2 is the weight coefficient of fluctuation similarity.

[0111] In some embodiments of the present application, a control simulation is performed based on the initial control method to obtain a simulated change feature of each real-time combustion state parameter, including:

[0112] Performing a control simulation of the burner based on the initial control method to obtain a control simulation result, wherein the control simulation result includes a plurality of simulated combustion state parameters after the initial control method;

[0113] By comparing the simulated combustion state parameters with the corresponding real-time combustion state parameters, the simulated change value, simulated change trend and simulated change stability of each real-time combustion state parameter within the control simulation time of the initial control method are obtained;

[0114] The simulated change value, simulated change trend and simulated change stability of each real-time combustion state parameter are set as the first simulated change feature corresponding to the real-time combustion state parameter;

[0115] generating a simulated sub-evaluation value of the corresponding combustion evaluation index according to the simulated combustion state parameter associated with the corresponding combustion evaluation index, and setting a difference between the simulated sub-evaluation value and the first evaluation value of the sub-evaluation value as a second simulated change characteristic of the real-time combustion state parameter associated with the corresponding combustion evaluation index;

[0116] generating a simulated combustion evaluation value according to the plurality of simulated sub-evaluation values, and setting a simulated compensation coefficient according to a difference between the simulated combustion evaluation value and a second evaluation value of the real-time combustion evaluation value;

[0117] Generate a state coefficient corresponding to the real-time combustion state parameter according to the first simulated change characteristic, the second simulated change characteristic and the simulated compensation coefficient;

[0118] The calculation formula of the state coefficient is:

[0119]

[0120] Among them, U is the state coefficient, r is the simulation compensation coefficient, c1 is the first state conversion coefficient, v1 is the weight coefficient of the first simulation change feature, B is the simulation change value, K is the simulation change stability, p is the simulation change trend, when the simulation change trend is a normal trend, p=1, when the simulation change trend is an abnormal trend, p=-1, c2 is the second state conversion coefficient, v2 is the weight coefficient of the second simulation change feature, s is the total number of combustion evaluation indicators associated with the current real-time combustion state parameter, L1x is the simulation sub-evaluation value of the xth combustion evaluation indicator associated with the current simulated combustion state parameter, L0x is the sub-evaluation value of the xth combustion evaluation indicator associated with the real-time combustion state parameter corresponding to the current simulated combustion state parameter, and L1x-L0x is the first evaluation value difference of the xth combustion evaluation indicator.

[0121] In this embodiment, the simulation change stability is to set the collection time node within the control simulation duration in advance, obtain multiple values ​​of the same simulated combustion state parameter according to the collection time node and calculate the variance of the corresponding simulated combustion state parameter, and judge the stability according to the variance, that is, the larger the variance, the smaller the simulation change stability, and the smaller the variance, the greater the simulation change stability, and the value range of the simulation change stability is (0, 1).

[0122] In this embodiment, the simulated change trend includes a normal trend and an abnormal trend. The normal trend means that the simulated combustion state parameters are closer to the standard combustion state parameters than the corresponding real-time combustion state parameters, and the abnormal trend means that the simulated combustion state parameters are farther away from the standard combustion state parameters than the corresponding real-time combustion state parameters.

[0123] In this embodiment, the simulation compensation coefficient is set according to the second evaluation value difference, the second evaluation value difference = simulated combustion evaluation value - real-time combustion evaluation value. When the second evaluation value difference is greater than 0 and the larger it is, the larger the simulation compensation coefficient is. When the second evaluation value difference is less than 0 and the smaller it is, the smaller the simulation compensation coefficient is. The value range of the simulation compensation coefficient is (0.75, 1.25).

[0124] In this embodiment, the state coefficient of each real-time combustion state parameter is calculated by using the first simulated change characteristic, the second simulated change characteristic and the simulated compensation coefficient to improve the accuracy of the state coefficient, thereby laying the foundation for the subsequent optimization of the corresponding control parameters in the initial control method, thereby improving the control efficiency and control accuracy of the control method and improving the combustion performance of the burner.

[0125] In some embodiments of the present application, the corresponding control parameters in the initial control method are optimized according to the simulated change characteristics, including:

[0126] Screen out the real-time combustion state parameters whose state coefficients are less than a preset state coefficient threshold value, and set them as the state parameters to be optimized;

[0127] Obtaining a historical control log of the state parameter to be optimized, and determining a control parameter associated with each state parameter to be optimized according to the degree of synchronous change between the historical control parameters involved in the historical control log and the state parameter to be optimized;

[0128] Determining the control parameters to be optimized in the initial control method according to the control parameters associated with each state parameter to be optimized;

[0129] The correction coefficient of the control parameter to be optimized in the initial control method is determined according to the state coefficient difference between each state parameter to be optimized and a preset state coefficient threshold.

[0130] In this embodiment, the control parameters in the initial control method include fuel flow, air volume, wind speed, wind volume, flame temperature, etc.

[0131] In this embodiment, the degree of synchronous change refers to the degree of change of the state parameter to be optimized caused by the change of the historical control parameter within a preset time period. When the degree of synchronous change is greater than the preset synchronous change degree threshold, the corresponding historical control parameter is set as the control parameter associated with the current state parameter to be optimized.

[0132] In this embodiment, the correction coefficient determined according to the state coefficient difference is set according to the historical state coefficient difference. The associated control parameters are set by the correction coefficient to continuously optimize the control efficiency and control accuracy of the initial control method to ensure efficient and stable operation of the burner.

[0133] In some embodiments of the present application, an optimization control method is obtained, including:

[0134] Based on the correction coefficient, the control parameters that need to be optimized in the initial control method are corrected to obtain the optimized control parameters;

[0135] The optimized control parameters are used to replace the corresponding control parameters in the initial control method to obtain the optimized control method.

[0136] In some embodiments of the present application, Figure 2 As shown, it also includes a burner optimization combustion control system:

[0137] An acquisition module is used to acquire real-time combustion state parameters, evaluate the real-time combustion state parameters based on multiple combustion evaluation indicators, and obtain a real-time combustion evaluation value;

[0138] A determination module, used to determine a preset control model according to the difference in the combustion evaluation values ​​combined with the real-time operating conditions when the real-time combustion evaluation value is less than the standard combustion evaluation value, and obtain an initial control method for the burner;

[0139] The control module is used to perform control simulation based on the initial control method to obtain the simulated change characteristics of each real-time combustion state parameter, optimize the corresponding control parameters in the initial control method according to the simulated change characteristics, obtain the optimized control method, and generate the control instructions of the burner according to the optimized control method.

[0140] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A burner optimization combustion control method, characterized in that: include: Acquire real-time combustion state parameters, evaluate the real-time combustion state parameters based on multiple combustion evaluation indicators, and obtain a real-time combustion evaluation value; When the real-time combustion evaluation value is less than the standard combustion evaluation value, the preset control model is determined according to the difference in the combustion evaluation values ​​combined with the real-time operating conditions, and the initial control method of the burner is obtained; A control simulation is performed based on the initial control method to obtain the simulated change characteristics of each real-time combustion state parameter. The corresponding control parameters in the initial control method are optimized according to the simulated change characteristics to obtain an optimized control method. The control instructions of the burner are generated according to the optimized control method.

2. The burner optimization combustion control method according to claim 1, characterized in that: The real-time combustion state parameters are evaluated based on multiple combustion evaluation indicators to obtain real-time combustion evaluation values, including: Pre-set multiple combustion evaluation indicators; Determining the real-time combustion state parameter associated with each combustion evaluation index according to the degree of association between the real-time combustion state parameter and the combustion evaluation index; Comparing the real-time combustion state parameter associated with each combustion evaluation index with the corresponding standard combustion state parameter to obtain a plurality of real-time combustion state parameter difference values, and generating a sub-evaluation value of the corresponding combustion evaluation index; A real-time combustion evaluation value is generated according to the sub-evaluation values ​​of the plurality of combustion evaluation indicators and the corresponding weight coefficients.

3. The burner optimization combustion control method according to claim 2, characterized in that: When the real-time combustion evaluation value is less than the standard combustion evaluation value, the preset control model is determined according to the difference in the combustion evaluation value combined with the real-time operating conditions, including: When the real-time combustion evaluation value is less than the standard combustion evaluation value, the combustion evaluation value difference is calculated and the real-time operating condition of the current burner is obtained; Perform similarity analysis on the real-time operating conditions and the historical operating conditions in the operating condition record table to obtain comprehensive similarity; Obtain a historical control reference library of historical operating conditions with the greatest comprehensive similarity to the real-time operating conditions, and build a preset control model based on the current historical control reference library; The historical control reference library includes a plurality of preset combustion evaluation value differences, and each preset combustion evaluation value difference is associated with a specific preset control method.

4. The burner optimization combustion control method according to claim 3, characterized in that: The initial control method of the burner is obtained, including: Based on several preset combustion evaluation value differences in the current historical control reference library as training input data and corresponding preset control methods as training output data, neural network training is performed to obtain a preset control model; Inputting the combustion evaluation value difference into a preset control model to obtain a plurality of first control methods; Compare the multiple control parameters in the first control method with the corresponding real-time control parameters respectively and predict the predicted control time, predicted control cost and predicted control stability of the corresponding control parameters; Generate a prediction control evaluation value corresponding to the first control method according to the prediction control duration, the prediction control cost and the prediction control stability; The first control method having the largest predictive control evaluation value is set as the initial control method.

5. The burner optimization combustion control method according to claim 4, characterized in that: The real-time operating conditions are analyzed for similarity with the historical operating conditions in the operating condition record table to obtain a comprehensive similarity, including: Preset multiple working condition evaluation indicators, and generate historical comprehensive working condition evaluation values ​​of multiple working condition evaluation indicators based on historical operating conditions; Based on each historical operating condition parameter in the historical operating condition as the horizontal coordinate and the historical comprehensive operating condition evaluation value as the vertical coordinate, the operating condition relationship curve under different preset time lengths is constructed; Comparing the correlation of the same historical operating condition parameter under different preset durations according to multiple operating condition relationship curves, and setting the preset duration with the greatest correlation as the target duration corresponding to the historical operating condition parameter; The target durations of multiple historical working conditions are averaged to obtain the standard duration; Taking the standard time length as the time reference line, setting multiple collection nodes at preset time intervals, obtaining multiple real-time operating condition parameters of the real-time operating condition and multiple historical operating condition parameters of the historical operating condition according to the collection nodes, and mapping them to the time reference line to generate a working condition parameter comparison reference diagram; Calculate the difference between each real-time operating condition parameter and the corresponding historical operating condition parameter in the operating condition parameter comparison reference diagram at each acquisition node, and generate a difference similarity based on multiple operating condition parameter differences at multiple acquisition nodes; Calculate the fluctuation value difference of each real-time operating condition parameter of the real-time operating condition in the operating condition comparison reference diagram and the historical operating condition parameter corresponding to the historical operating condition at each acquisition node, and generate fluctuation similarity according to multiple fluctuation value differences at multiple acquisition nodes; Generate comprehensive similarity based on difference similarity and fluctuation similarity.

6. The burner optimization combustion control method according to claim 5, characterized in that: Generate comprehensive similarity based on difference similarity and fluctuation similarity, including: The calculation formula of the comprehensive similarity is: Among them, H is the comprehensive similarity, g1 is the weight coefficient of difference similarity, y1i,z is the i-th real-time operating condition parameter at the z-th acquisition node, △yi,z is the difference of the i-th operating condition parameter at the z-th acquisition node, n is the total number of real-time operating condition parameters of real-time operation conditions, m is the total number of acquisition nodes, △wi,z is the i-th fluctuation value difference at the z-th acquisition node, and g2 is the weight coefficient of fluctuation similarity.

7. The burner optimization combustion control method according to claim 6, characterized in that: Based on the initial control method, control simulation is performed to obtain the simulated change characteristics of each real-time combustion state parameter, including: Performing a control simulation of the burner based on the initial control method to obtain a control simulation result, wherein the control simulation result includes a plurality of simulated combustion state parameters after the initial control method; By comparing the simulated combustion state parameters with the corresponding real-time combustion state parameters, the simulated change value, simulated change trend and simulated change stability of each real-time combustion state parameter within the control simulation time of the initial control method are obtained; The simulated change value, simulated change trend and simulated change stability of each real-time combustion state parameter are set as the first simulated change feature corresponding to the real-time combustion state parameter; generating a simulated sub-evaluation value of the corresponding combustion evaluation index according to the simulated combustion state parameter associated with the corresponding combustion evaluation index, and setting a difference between the simulated sub-evaluation value and the first evaluation value of the sub-evaluation value as a second simulated change characteristic of the real-time combustion state parameter associated with the corresponding combustion evaluation index; generating a simulated combustion evaluation value according to the plurality of simulated sub-evaluation values, and setting a simulated compensation coefficient according to a difference between the simulated combustion evaluation value and a second evaluation value of the real-time combustion evaluation value; Generate a state coefficient corresponding to the real-time combustion state parameter according to the first simulated change characteristic, the second simulated change characteristic and the simulated compensation coefficient; The calculation formula of the state coefficient is: Among them, U is the state coefficient, r is the simulation compensation coefficient, c1 is the first state conversion coefficient, v1 is the weight coefficient of the first simulation change feature, B is the simulation change value, K is the simulation change stability, p is the simulation change trend, when the simulation change trend is a normal trend, p=1, when the simulation change trend is an abnormal trend, p=-1, c2 is the second state conversion coefficient, v2 is the weight coefficient of the second simulation change feature, s is the total number of combustion evaluation indicators associated with the current real-time combustion state parameter, L1x is the simulation sub-evaluation value of the xth combustion evaluation indicator associated with the current simulated combustion state parameter, L0x is the sub-evaluation value of the xth combustion evaluation indicator associated with the real-time combustion state parameter corresponding to the current simulated combustion state parameter, and L1x-L0x is the first evaluation value difference of the xth combustion evaluation indicator.

8. The burner optimization combustion control method according to claim 7, characterized in that: According to the simulated change characteristics, the corresponding control parameters in the initial control method are optimized, including: Screen out the real-time combustion state parameters whose state coefficients are less than a preset state coefficient threshold value, and set them as the state parameters to be optimized; Obtaining a historical control log of the state parameter to be optimized, and determining a control parameter associated with each state parameter to be optimized according to the degree of synchronous change between the historical control parameters involved in the historical control log and the state parameter to be optimized; Determining the control parameters to be optimized in the initial control method according to the control parameters associated with each state parameter to be optimized; The correction coefficient of the control parameter to be optimized in the initial control method is determined according to the state coefficient difference between each state parameter to be optimized and a preset state coefficient threshold.

9. The burner optimization combustion control method according to claim 8, characterized in that: The optimized control method is obtained, including: Based on the correction coefficient, the control parameters that need to be optimized in the initial control method are corrected to obtain the optimized control parameters; The optimized control parameters are used to replace the corresponding control parameters in the initial control method to obtain the optimized control method.

10. A burner optimized combustion control system, characterized in that: include: An acquisition module is used to acquire real-time combustion state parameters, evaluate the real-time combustion state parameters based on multiple combustion evaluation indicators, and obtain a real-time combustion evaluation value; A determination module, used to determine a preset control model according to the difference in the combustion evaluation values ​​combined with the real-time operating conditions when the real-time combustion evaluation value is less than the standard combustion evaluation value, and obtain an initial control method for the burner; The control module is used to perform control simulation based on the initial control method to obtain the simulated change characteristics of each real-time combustion state parameter, optimize the corresponding control parameters in the initial control method according to the simulated change characteristics, obtain the optimized control method, and generate the control instructions of the burner according to the optimized control method.

Images