An energy-saving optimization method and system based on steam boiler combustion status monitoring

Abstract

This application provides an energy-saving optimization method and system based on combustion state monitoring of a steam boiler. It acquires combustion state time-series data for the current optimization cycle, back-maps the sampling times of each parameter in the combustion state time-series data to obtain the combustion activation time of each parameter; based on the combustion activation times of each parameter, it determines the air supply arrival time and fuel arrival time, thus obtaining the air-fuel timing deviation; based on the combustion activation times and state change amplitudes of each parameter, it determines the air supply degree and fuel arrival degree, and combines this with the target air-fuel ratio to generate the air-fuel ratio deviation; based on the air-fuel timing deviation and air-fuel ratio deviation, it corrects the set air supply volume and set fuel quantity for the next optimization cycle, thereby generating an optimization control command and issuing it to the boiler combustion execution unit. This application can combine the air-fuel timing deviation and the ratio deviation to synergistically correct the air supply volume and fuel quantity, thereby improving the combustion efficiency and energy-saving control level of the steam boiler.

Description

Technical Field

[0001] This application relates to the field of steam boiler combustion optimization control technology, and more specifically, to an energy-saving optimization method and system based on steam boiler combustion status monitoring. Background Technology

[0002] Steam boilers are core thermal equipment in industrial production and energy supply. The stability and economy of their combustion conditions directly determine the equipment's operating efficiency, fuel consumption, and pollutant emission indicators. Currently, steam boiler combustion control relies heavily on experience to set parameters and adjusts them in conjunction with operating data such as flue gas oxygen content, furnace temperature, and steam pressure. Due to the dynamic lag and multivariate coupling characteristics of the combustion system, there is a time deviation between the sampling time of each parameter and the actual combustion effect time in the furnace. Traditional control methods cannot accurately reflect the true matching state of air supply and fuel in the combustion zone.

[0003] However, existing combustion optimization methods mostly focus on the static proportioning adjustment of total air volume or total coal quantity, lacking joint analysis of the timing relationship and actual arrival degree of air and fuel. This can easily lead to situations such as air supply leading and fuel lag, or fuel leading and insufficient air supply, which in turn causes the air-fuel ratio to deviate from the ideal state, resulting in incomplete combustion, decreased thermal efficiency, and increased energy consumption. Therefore, how to combine air-fuel timing deviations and proportioning deviations to synergistically correct air volume and fuel quantity, thereby improving the combustion efficiency and energy-saving control level of steam boilers, is a problem facing the industry. Summary of the Invention

[0004] This application provides an energy-saving optimization method and system based on steam boiler combustion status monitoring, which can combine air-fuel timing deviation and ratio deviation to synergistically correct the air supply volume and fuel quantity, thereby improving the combustion efficiency and energy-saving control level of the steam boiler.

[0005] In a first aspect, this application provides an energy-saving optimization method based on steam boiler combustion status monitoring, comprising the following steps:

[0006] Obtain the combustion state time-series data of the steam boiler in the current optimization cycle, and backtrack and map the key sampling times of each parameter in the combustion state time-series data to obtain the combustion effective time of each parameter at the furnace combustion interface.

[0007] Based on the combustion activation time of each parameter, the air supply arrival time and fuel arrival time are determined, thereby obtaining the air-fuel timing deviation;

[0008] Based on the combustion activation time and state change amplitude of each parameter, the degree of air supply and fuel supply are determined. The air supply and fuel supply are then matched with the target air-fuel ratio to generate the air-fuel ratio deviation.

[0009] Based on the air-fuel timing deviation and the air-fuel ratio deviation, the set air supply volume and set fuel quantity for the next optimization cycle are corrected. An optimization control command is generated based on the corrected set air supply volume and set fuel quantity and sent to the boiler combustion execution unit.

[0010] In some embodiments, back-mapping is performed on the key sampling times of each parameter in the combustion state time series data to obtain the combustion activation time of each parameter at the furnace combustion interface, specifically including:

[0011] Obtain adjustment instruction information within the current optimization cycle, the adjustment instruction information including air supply adjustment items and fuel adjustment items, and record the issuance time of the air supply adjustment items and the fuel adjustment items respectively;

[0012] The change characteristic moments corresponding to each parameter are obtained from the combustion state time series data;

[0013] Based on the response correlation between each parameter and the air supply adjustment item and the fuel adjustment item, determine the backtracking benchmark adjustment item corresponding to each parameter;

[0014] Based on the issuance time of the backtracking benchmark adjustment term and the change characteristic time of the corresponding parameter, the comprehensive response delay corresponding to each parameter is determined;

[0015] Based on the comprehensive response delay corresponding to each parameter, the key sampling time of each parameter is back-mapped to obtain the combustion effective time of each parameter at the furnace combustion interface.

[0016] In some embodiments, obtaining the change characteristic moments corresponding to each parameter in the combustion state time series data specifically includes:

[0017] Extract the time-series curves corresponding to each parameter from the combustion state time-series data and smooth the time-series curves to obtain the denoised parameter time-series curves.

[0018] The parameter time series curve is dynamically differentially analyzed by a preset sliding time window to obtain the rate of change increment of the parameter time series curve. The moment when the rate of change increment reaches the preset increment threshold corresponding to the parameter is determined as the change characteristic moment of the parameter.

[0019] By iterating through all parameters, the characteristic moments of change of each parameter in the combustion state time series data are obtained in turn.

[0020] In some embodiments, based on the combustion activation time of each parameter, the air supply arrival time and fuel arrival time are determined, thereby obtaining the air-fuel timing deviation, specifically including:

[0021] Obtain the air supply response sensitivity coefficient of each parameter relative to the air supply channel, the fuel response sensitivity coefficient relative to the fuel channel, and the corresponding time series reliability coefficient under the current optimization cycle;

[0022] The combustion activation time corresponding to each parameter is used as the candidate time.

[0023] Feature correlation analysis is performed based on the air supply response sensitivity coefficient and the time series reliability coefficient to construct the air supply time series weight for each candidate moment, and the fuel time series weight corresponding to each candidate moment is determined according to the fuel response sensitivity coefficient and the time series reliability coefficient.

[0024] Based on each candidate moment and its corresponding air supply timing weight, the air supply timing consistency fusion is performed to obtain the air supply arrival moment of the air supply channel.

[0025] Fuel arrival times of the fuel channel are obtained by performing fuel time sequence consistency fusion based on each candidate time and its corresponding fuel time sequence weight.

[0026] Based on the arrival time of the air supply and the arrival time of the fuel, the timing characteristics are calculated to generate the air-fuel timing deviation.

[0027] In some embodiments, determining the degree of air supply and fuel supply based on the combustion activation time and state change amplitude of each parameter specifically includes:

[0028] Normalize the magnitude of the state change of each parameter to obtain the corresponding relative change;

[0029] Based on the time proximity between the combustion activation time of each parameter and the air supply arrival time, the air supply synchronization coefficient corresponding to each parameter is determined.

[0030] Based on the time proximity between the combustion activation time of each parameter and the fuel arrival time, the fuel synchronization coefficient corresponding to each parameter is determined;

[0031] Based on the relative change of the same parameter, the air supply synchronization coefficient, and the air supply response sensitivity coefficient, a collaborative mapping is performed to obtain the air supply contribution value of the parameter. The air supply contribution values ​​of all parameters are integrated and processed to obtain the degree of air supply arrival.

[0032] Based on the relative change of the same parameter, the fuel synchronization coefficient, and the fuel response sensitivity coefficient, a collaborative mapping is performed to obtain the fuel contribution value of the parameter. The fuel contribution values ​​of all parameters are then integrated to obtain the fuel availability.

[0033] In some embodiments, the air supply level and the fuel supply level are combined with the target air-fuel ratio to generate an air-fuel ratio deviation, specifically including:

[0034] Obtain the dynamic characteristic parameters of the boiler combustion system;

[0035] The ideal air-fuel ratio is determined based on the target air-fuel ratio corresponding to the current optimization cycle and the dynamic characteristic parameters.

[0036] The air supply level is mapped to the fuel supply level to obtain the actual air-fuel ratio, and then the air-fuel ratio deviation of the actual air-fuel ratio relative to the ideal air-fuel ratio is determined.

[0037] The air-fuel ratio deviation is subjected to dead-zone filtering and amplitude limiting to obtain the air-fuel ratio deviation.

[0038] In some embodiments, correcting the set air supply volume and set fuel quantity for the next optimization cycle based on the air-fuel timing deviation and the air-fuel ratio deviation specifically includes:

[0039] The wind coal timing deviation and the wind coal ratio deviation are respectively subjected to direction-amplitude normalization to obtain the wind coal timing compensation amount and the wind coal ratio compensation amount.

[0040] Based on the wind-coal timing compensation amount, the air supply timing correction component and the fuel timing correction component are determined according to the preset timing correction rules. Based on the wind-coal ratio compensation amount, the air supply ratio correction component and the fuel ratio correction component are determined according to the preset ratio correction rules.

[0041] Adaptive fusion processing is performed on the air supply timing correction component and the air supply ratio correction component to obtain the air supply correction amount; adaptive fusion processing is performed on the fuel timing correction component and the fuel ratio correction component to obtain the fuel correction amount.

[0042] The air supply volume correction is used to limit the adjustment of the basic air supply volume for the next optimization cycle to obtain the set air supply volume. The fuel quantity correction is used to limit the adjustment of the basic fuel quantity for the next optimization cycle to obtain the set fuel quantity.

[0043] Secondly, this application provides an energy-saving optimization system based on steam boiler combustion state monitoring, used to execute an energy-saving optimization method based on steam boiler combustion state monitoring, including:

[0044] The time-series backtracking module is used to acquire the combustion state time-series data of the steam boiler in the current optimization cycle, and to backtrack and map the key sampling times of each parameter in the combustion state time-series data to obtain the combustion effective time of each parameter at the furnace combustion interface.

[0045] The deviation determination module is used to determine the air supply arrival time and fuel arrival time based on the combustion activation time of each parameter, thereby obtaining the air-fuel timing deviation.

[0046] The deviation determination module is also used to determine the degree of air supply and the degree of fuel supply based on the combustion activation time and state change amplitude of each parameter, and to combine the degree of air supply and the degree of fuel supply with the target air-fuel ratio to generate the air-fuel ratio deviation.

[0047] The energy-saving control module is used to correct the set air volume and set fuel volume for the next optimization cycle based on the air-fuel timing deviation and the air-fuel ratio deviation, and to generate an optimization control command based on the corrected set air volume and set fuel volume and send it to the boiler combustion execution unit.

[0048] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, the processor being configured to acquire the code and execute the above-described energy-saving optimization method based on steam boiler combustion status monitoring.

[0049] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described energy-saving optimization method based on monitoring the combustion status of a steam boiler.

[0050] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0051] This application provides an energy-saving optimization method and system based on steam boiler combustion state monitoring. The method involves acquiring combustion state time-series data of the steam boiler in the current optimization cycle, back-mapping the key sampling times of each parameter in the combustion state time-series data to obtain the combustion activation time of each parameter at the furnace combustion interface, determining the air supply arrival time and fuel arrival time based on the combustion activation times of each parameter, and thus obtaining the air-fuel timing deviation, determining the air supply degree and fuel arrival degree based on the combustion activation times and state change amplitude of each parameter, and combining the target air-fuel ratio to proportion the air supply degree and fuel arrival degree to generate an air-fuel ratio deviation, correcting the set air supply volume and set fuel quantity for the next optimization cycle based on the corrected set air supply volume and set fuel quantity, generating an optimization control command based on the corrected set air supply volume and set fuel quantity, and issuing it to the boiler combustion execution unit.

[0052] Therefore, this application demonstrates that, firstly, by calculating the total response delay between the change characteristic moment and the retrospective baseline adjustment term issuance moment, and combining this with the channel pre-deployment delay to obtain the comprehensive response delay, it is possible to distinguish the time lag of different stages, making the delay analysis more consistent with the actual physical mechanism of the boiler combustion process. Based on the comprehensive response delay, the key sampling moments of each parameter are retrospectively analyzed to obtain the combustion effectiveness moment of each parameter at the furnace combustion interface. This allows the sampling moments obtained from external monitoring to be corrected to the actual effective time of the regulating medium in the combustion zone, improving the accuracy and stability of steam boiler combustion status monitoring and energy-saving optimization control. Secondly, by using the combustion effectiveness moment of each parameter as a candidate moment, and integrating multiple types of response sensitivity coefficients and time-series reliability coefficients to construct weights and achieve consistent fusion, the application avoids the random errors present in single-parameter judgments, ensuring that the air supply arrival moment and fuel arrival moment truly reflect the actual operating state of the furnace air and coal. Then, by solving for the air supply and fuel supply levels through multi-parameter weighted integration, the influence of single parameters on on-site noise interference can be reduced. Dynamically correcting the target air-fuel ratio based on boiler dynamic characteristic parameters can adaptively adapt to complex actual operating conditions such as load fluctuations and coal quality changes, improving the operating condition adaptability of the air-fuel ratio calculation. Combining dead-zone filtering and amplitude limiting processing can avoid frequent system adjustments caused by small disturbances, effectively improving the operational stability of the boiler combustion control system. Finally, the air-fuel timing deviation and ratio deviation are jointly used to correct the air supply and fuel quantity, and direction-amplitude normalization, adaptive weight fusion, and amplitude limiting safety constraints are introduced. This ensures accurate compensation for air-fuel mismatch problems while also taking into account response priorities and operational safety under different operating conditions, improving the overall robustness of boiler combustion energy-saving optimization control.

[0053] In summary, the technical solution adopted in this application can combine the timing deviation of air and coal and the ratio deviation to synergistically correct the air supply volume and fuel quantity, thereby improving the combustion efficiency and energy-saving control level of the steam boiler. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is an exemplary flowchart of an energy-saving optimization method based on steam boiler combustion status monitoring, according to some embodiments of this application;

[0056] Figure 2 This is a schematic diagram illustrating an application scenario of an energy-saving optimization method based on steam boiler combustion status monitoring, according to some embodiments of this application.

[0057] Figure 3 This is an exemplary flowchart illustrating the timing of combustion activation of various parameters at the furnace combustion interface, as shown in some embodiments of this application.

[0058] Figure 4 This is a schematic diagram of the structure of an energy-saving optimization system based on steam boiler combustion status monitoring, according to some embodiments of this application;

[0059] Figure 5 This is a schematic diagram of the structure of a computer device for implementing an energy-saving optimization method based on steam boiler combustion status monitoring, according to some embodiments of this application. Detailed Implementation

[0060] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0061] This application provides an energy-saving optimization method and system based on steam boiler combustion state monitoring. The core of the method is to acquire the combustion state time-series data of the steam boiler in the current optimization cycle, back-map the key sampling times of each parameter in the combustion state time-series data to obtain the combustion activation time of each parameter at the furnace combustion interface, determine the air supply arrival time and fuel arrival time based on the combustion activation times of each parameter, and thus obtain the air-fuel timing deviation, determine the air supply degree and fuel arrival degree based on the combustion activation times and state change amplitudes of each parameter, and combine the air supply degree and fuel arrival degree with the target air-fuel ratio to generate an air-fuel ratio deviation, and correct the set air supply volume and set fuel quantity for the next optimization cycle based on the air supply volume and set fuel quantity. An optimization control command is generated based on the corrected set air supply volume and set fuel quantity and sent to the boiler combustion execution unit. This scheme can combine the air-fuel timing deviation and the ratio deviation to synergistically correct the air supply volume and fuel quantity, thereby improving the combustion efficiency and energy-saving control level of the steam boiler.

[0062] To better understand the above technical solutions, a detailed description of the technical solutions will be provided below in conjunction with the accompanying drawings and specific embodiments. (Refer to...) Figure 1 The figure is an exemplary flowchart of an energy-saving optimization method based on steam boiler combustion status monitoring, according to some embodiments of this application. The figure mainly includes the following steps:

[0063] In step S101, the combustion state time series data of the steam boiler in the current optimization cycle is obtained, and the key sampling time of each parameter in the combustion state time series data is back-mapped to obtain the combustion effective time of each parameter at the furnace combustion interface.

[0064] It should be noted that, Figure 2 This is a schematic diagram of an application scenario for an energy-saving optimization method based on steam boiler combustion status monitoring, according to some embodiments of this application. As shown in the figure, a flue gas oxygen content sensor and a flue gas temperature sensor are respectively installed at the flue of the steam boiler, and a steam flow meter is installed on the steam pipeline to collect the combustion status parameters of the steam boiler.

[0065] In specific implementation, within the current optimization cycle of the steam boiler, the current optimization cycle is divided according to a preset time length, for example, 5 minutes as an optimization cycle. The aforementioned sensors continuously collect combustion state parameters with a fixed sampling period of 1 second. The combustion state parameters include flue gas oxygen content, exhaust gas temperature, and steam flow rate, generating original time-series data sequences corresponding to each parameter. Time synchronization processing and data validity verification are performed on all original time-series data sequences in sequence. After removing invalid data, valid time-series data corresponding to each parameter is obtained. All valid time-series data are integrated according to a unified sampling time to form the combustion state time-series data for the current optimization cycle.

[0066] It should be noted that the oxygen content of the flue gas is used to characterize the excess air level in the furnace combustion; the flue gas temperature reflects the waste heat release and heat exchange conditions of the flue gas; and the steam flow rate is used to reflect the real-time operating load of the boiler.

[0067] Preferably, in some embodiments, reference is made to Figure 3 As shown in the figure, this is an exemplary flowchart illustrating the process of obtaining the combustion activation time of each parameter at the furnace combustion interface according to some embodiments of this application. In this embodiment, the key sampling times of each parameter in the combustion state time series data are back-mapped to obtain the combustion activation time of each parameter at the furnace combustion interface, which can be achieved by the following steps:

[0068] In step S1011, the adjustment instruction information within the current optimization cycle is obtained. The adjustment instruction information includes air supply adjustment items and fuel adjustment items, and the issuance time of the air supply adjustment items and the fuel adjustment items is recorded respectively.

[0069] In step S1012, the change characteristic time corresponding to each parameter is obtained from the combustion state time series data;

[0070] In step S1013, the backtracking reference adjustment item corresponding to each parameter is determined based on the response correlation between each parameter and the air supply adjustment item and the fuel adjustment item.

[0071] In step S1014, based on the issuance time of the backtracking benchmark adjustment term and the change characteristic time of the corresponding parameter, the comprehensive response delay corresponding to each parameter is determined;

[0072] In step S1015, the key sampling time of each parameter is back-mapped according to the comprehensive response delay corresponding to each parameter to obtain the combustion effective time of each parameter at the furnace combustion interface.

[0073] In specific implementation, firstly, the adjustment instruction information issued to the boiler combustion execution unit within the current optimization cycle is obtained. This information includes air supply adjustment items and fuel adjustment items. The issuance time of the air supply adjustment items and the fuel adjustment items is recorded respectively. The air supply adjustment items are used to characterize the adjustment content of the air supply setpoint, and the fuel adjustment items are used to characterize the adjustment content of the fuel quantity setpoint. Secondly, the effective time series data of each parameter in the combustion state time series data is segmented according to a fixed step size to obtain multiple continuous time series segments. The cosine similarity algorithm is used to calculate the feature similarity between adjacent segments in turn. A similarity threshold is set for each parameter. When the similarity between adjacent segments is lower than the threshold, it is determined that the parameter state has undergone a significant change and the corresponding time is recorded. If multiple change times are detected for the same parameter, the first change time within the optimization cycle is selected as the change feature time of the parameter. The fixed step size and the similarity threshold are pre-calibrated according to the historical operating conditions of the steam boiler. The segmentation, similarity calculation and change judgment process is repeated to traverse all parameters and obtain the change feature time corresponding to each parameter one by one.

[0074] It should be noted that the aforementioned response correlation can be determined based on the boiler combustion mechanism, historical operating data, or pre-calibrated results. It is used to characterize the sensitivity of different parameters to air supply regulation and fuel regulation. For example, the oxygen content in flue gas can directly reflect the excess air in the furnace, and its change is mainly affected by air supply regulation. Therefore, its retrospective benchmark regulation item is preset as the air supply regulation item. Steam flow directly reflects the fuel heat release level. Therefore, its retrospective benchmark regulation item is preset as the fuel regulation item. The flue gas temperature is affected by both air supply and fuel quantity. Step excitation needs to be applied to the air supply regulation item and the fuel regulation item respectively. The flue gas temperature response curves corresponding to the two types of regulation items are collected, and the response amplitude and response speed of the curves are extracted. The fusion weights of the two features are pre-calibrated in combination with the boiler historical operating sample library. The response sensitivity coefficient is calculated by weighted fusion according to the weights, and the regulation item with the larger coefficient is selected as the retrospective benchmark regulation item corresponding to the flue gas temperature.

[0075] In specific implementation, based on the aforementioned response correlation, it is determined whether each parameter is mainly affected by air supply regulation or fuel regulation, thereby determining the corresponding retrospective reference regulation item for each parameter. If the retrospective reference regulation item is an air supply regulation item, the parameter is assigned to the air supply channel; if it is a fuel regulation item, it is assigned to the fuel channel. Then, for each parameter, the extracted change characteristic time is taken as the response endpoint, and the issuance time of the retrospective reference regulation item is taken as the time reference. The time difference between the two is calculated to obtain the total response delay corresponding to the parameter. Since the time taken for the regulation command to be issued from the control system to the execution unit, and then through the action of the execution unit and the medium delivery, until the air or fuel actually reaches the combustion interface of the furnace, is called the pre-arrival delay of the regulation channel; and the total response delay includes not only the pre-arrival delay, but also the combustion physical process and sensor response time corresponding to the parameter change after the medium arrives at the combustion interface; therefore, by subtracting the pre-arrival delay of the corresponding channel from the total response delay of the parameter, the comprehensive response delay corresponding to the parameter can be obtained. Finally, the node where the parameter begins to undergo substantial changes is taken as the critical sampling moment, that is, the moment of change of the parameter is taken as the critical sampling moment. The response delay is traced back in reverse to solve for the combustion effective moment of the parameter at the furnace combustion interface. The above calculation steps are repeated for all parameters to obtain the combustion effective moment of each parameter one by one.

[0076] It should be noted that the aforementioned pre-delay is used to characterize the time required for the adjustment command to be issued and then act on the combustion interface of the furnace, and can be obtained by pre-measurement based on the current operating conditions; the aforementioned comprehensive response delay reflects the time difference from when the air or coal actually arrives at the combustion interface to when the parameters begin to change, and is mainly affected by factors such as the combustion chemical reaction rate, heat transfer process, and sensor inertia; the aforementioned combustion activation time refers to the time node when the air supply or fuel adjustment medium actually arrives at the combustion interface of the furnace and begins to trigger parameter changes, reflecting the actual effective time of the adjustment action in the combustion zone.

[0077] In addition, in some embodiments, the specific method for obtaining the change characteristic time of each parameter in the combustion state time series data can be as follows:

[0078] Extract the time-series curves corresponding to each parameter from the combustion state time-series data and smooth the time-series curves to obtain the denoised parameter time-series curves.

[0079] The parameter time series curve is dynamically differentially analyzed by a preset sliding time window to obtain the rate of change increment of the parameter time series curve. The moment when the rate of change increment reaches the preset increment threshold corresponding to the parameter is determined as the change characteristic moment of the parameter.

[0080] By iterating through all parameters, the characteristic moments of change of each parameter in the combustion state time series data are obtained in turn.

[0081] In specific implementation, firstly, the time-series curves corresponding to each parameter are extracted from the combustion state time-series data, and a first-order low-pass filter with a cutoff frequency of 0.1Hz is used to denoise and smooth each time-series curve to obtain the denoised parameter time-series curves for each parameter. Then, for each denoised parameter time-series curve, a sliding time window with a length of 5 seconds is used to slide point by point along the time axis. Taking the current time as the boundary, the slope of parameter change in the data before and after the current time is calculated, and the difference between the two slopes is taken as the rate of change increment of the parameter at the current time. The length of the sliding time window and the preset increment threshold of each parameter are obtained by cross-calibration based on the industrial boiler industry standard operating condition dataset and the field historical operation sample library. When the rate of change increment at a certain time is greater than or equal to the preset increment threshold corresponding to the parameter, the time is marked as a candidate change feature time. To avoid misjudgment caused by occasional noise interference, the time with the largest rate of change increment value is selected as the unique change feature time of the parameter among all candidate times in the same optimization cycle. Finally, by iterating through all parameters in the manner described above, the characteristic moments of change of each parameter in the combustion state time series data are obtained in turn.

[0082] It should be noted that determining the corresponding retrospective baseline adjustment item for each parameter based on the response correlation enables different parameters to establish a matching relationship with air supply regulation or fuel regulation, thereby improving the accuracy of parameter response attribution and providing a basis for subsequent delay calculations. By calculating the total response delay between the change characteristic moment and the issuance moment of the retrospective baseline adjustment item, and combining it with the corresponding channel's pre-positioning delay to obtain the comprehensive response delay, it is possible to distinguish the time lags of different stages such as control command issuance, actuator action, medium delivery, in-furnace combustion reaction, and sensor response, making the delay analysis more consistent with the actual physical mechanism of the boiler combustion process. Based on the comprehensive response delay, retrospectively analyzing the key sampling moments of each parameter yields the combustion effectiveness moment of each parameter at the furnace combustion interface. This allows the sampling moments obtained from external monitoring to be corrected to the actual time node when the regulating medium takes effect in the combustion zone, thus providing a reliable basis for subsequent calculations and improving the accuracy and stability of steam boiler combustion status monitoring and energy-saving optimization control.

[0083] In step S102, based on the combustion activation time of each parameter, the air supply arrival time and fuel arrival time are determined, thereby obtaining the air-fuel timing deviation.

[0084] In some embodiments, the timing of air supply arrival and fuel arrival are determined based on the combustion activation time of each parameter, thereby obtaining the air-fuel timing deviation. Specifically, this can be achieved in the following manner:

[0085] Obtain the air supply response sensitivity coefficient of each parameter relative to the air supply channel, the fuel response sensitivity coefficient relative to the fuel channel, and the corresponding time series reliability coefficient under the current optimization cycle;

[0086] The combustion activation time corresponding to each parameter is used as the candidate time.

[0087] Feature correlation analysis is performed based on the air supply response sensitivity coefficient and the time series reliability coefficient to construct the air supply time series weight for each candidate moment, and the fuel time series weight corresponding to each candidate moment is determined according to the fuel response sensitivity coefficient and the time series reliability coefficient.

[0088] Based on each candidate moment and its corresponding air supply timing weight, the air supply timing consistency fusion is performed to obtain the air supply arrival moment of the air supply channel.

[0089] Fuel arrival times of the fuel channel are obtained by performing fuel time sequence consistency fusion based on each candidate time and its corresponding fuel time sequence weight.

[0090] Based on the arrival time of the air supply and the arrival time of the fuel, the timing characteristics are calculated to generate the air-fuel timing deviation.

[0091] It should be noted that the air supply response sensitivity coefficient is used to characterize the sensitivity of each combustion parameter to the air supply adjustment item, and the fuel response sensitivity coefficient is used to characterize the sensitivity of each combustion parameter to the fuel adjustment item. Both types of response sensitivity coefficients can be pre-calibrated through regression analysis of boiler historical operating data and combustion mechanism simulation analysis. The time series reliability coefficient is used to characterize the accuracy of the combustion activation time obtained by solving each parameter. It is quantified based on the signal-to-noise ratio of the corresponding parameter at the characteristic time of change. The higher the signal-to-noise ratio, the higher the time series reliability of the corresponding combustion activation time.

[0092] In practice, firstly, the air supply response sensitivity coefficient, fuel response sensitivity coefficient, and timing reliability coefficient corresponding to each parameter within the current optimization cycle are read. Secondly, after obtaining the combustion activation time of each parameter, each combustion activation time is taken as a candidate time. Subsequently, for a single candidate time, its corresponding air supply response sensitivity coefficient and timing reliability coefficient are multiplied and fused to obtain the air supply timing weight for that candidate time. Using the same calculation logic, the fuel timing weight for that candidate time is calculated by combining the fuel response sensitivity coefficient and the timing reliability coefficient. Then, a weighted average calculation is performed using all candidate times as the calculation sample and the corresponding air supply timing weight as the weighting factor to obtain the air supply arrival time. Similarly, a weighted average is performed based on each candidate time and its corresponding fuel timing weight to obtain the fuel arrival time. Finally, the difference between the fuel arrival time and the air supply arrival time is calculated to generate the air-coal timing deviation: a positive difference indicates that the actual fuel arrival time is later than the air supply arrival time; a negative difference indicates that the actual fuel arrival time is earlier than the air supply arrival time. It should be noted that the air-coal timing deviation directly reflects the degree of timing mismatch between air and coal supply at the furnace combustion interface.

[0093] It should be noted that by taking the combustion activation time corresponding to multiple parameters as candidate times, and combining the three types of coefficients to construct weights and complete the fusion calculation, the random errors caused by the single parameter judgment result can be effectively eliminated, so that the obtained air supply arrival time and fuel arrival time truly reflect the actual operating status of air and coal in the furnace. By quantifying the order of air and coal supply through time difference, reliable data support can be provided for subsequent calculation of air and coal time compensation amount and correction of set air supply volume and set fuel amount.

[0094] In step S103, based on the combustion activation time and state change amplitude of each parameter, the air supply level and fuel supply level are determined, and the air supply level and fuel supply level are matched with the target air-fuel ratio to generate the air-fuel ratio deviation.

[0095] In some embodiments, the determination of the degree of air supply and fuel supply based on the combustion activation time and state change amplitude of each parameter can be achieved in the following manner:

[0096] Normalize the magnitude of the state change of each parameter to obtain the corresponding relative change;

[0097] Based on the time proximity between the combustion activation time of each parameter and the air supply arrival time, the air supply synchronization coefficient corresponding to each parameter is determined.

[0098] Based on the time proximity between the combustion activation time of each parameter and the fuel arrival time, the fuel synchronization coefficient corresponding to each parameter is determined;

[0099] Based on the relative change of the same parameter, the air supply synchronization coefficient, and the air supply response sensitivity coefficient, a collaborative mapping is performed to obtain the air supply contribution value of the parameter. The air supply contribution values ​​of all parameters are integrated and processed to obtain the degree of air supply arrival.

[0100] Based on the relative change of the same parameter, the fuel synchronization coefficient, and the fuel response sensitivity coefficient, a collaborative mapping is performed to obtain the fuel contribution value of the parameter. The fuel contribution values ​​of all parameters are then integrated to obtain the fuel availability.

[0101] It should be noted that the state change amplitude is used to quantify the degree of dynamic change of each parameter relative to the steady-state baseline condition within the current optimization cycle. Specifically, it is defined as the numerical difference between each parameter and the new steady-state value as it transitions from the initial steady-state value to the new steady-state value under the adjustment effect. It corresponds to the change amplitude of the parameter near the moment when combustion takes effect. For example, the difference between the flue gas oxygen content and the new steady-state value before and after the moment when combustion takes effect is the state change amplitude corresponding to the flue gas oxygen content.

[0102] In specific implementation, firstly, for each parameter, the ratio of its state change amplitude within the current optimization cycle to the maximum allowable change range calibrated under historical normal operating conditions is calculated to obtain a dimensionless relative change. Secondly, the absolute time difference between the combustion activation time and the air supply arrival time corresponding to the parameter is calculated, and this time difference is normalized using a preset linear decay function to convert it into a time proximity degree in the interval [0, 1]. The normalized time proximity degree is then assigned as the air supply synchronization coefficient of the corresponding parameter. The smaller the time difference between the combustion activation time and the air supply arrival time, the higher the time proximity degree, indicating better synchronization between the parameter response and the air supply adjustment action, and a larger corresponding air supply synchronization coefficient. Then, following the same calculation logic, the corresponding time proximity degree is obtained based on the time difference between the combustion activation time and the fuel arrival time of each parameter, thereby determining the fuel synchronization coefficient corresponding to each parameter. Next, for each parameter, its relative change, air supply synchronization coefficient, and air supply response sensitivity coefficient are multiplied together to obtain the air supply contribution value of that parameter. The arithmetic mean of the air supply contribution values ​​of all parameters is then calculated to obtain the air supply availability of the steam boiler in the current optimization cycle. Similarly, the relative change, fuel synchronization coefficient, and fuel response sensitivity coefficient of the same parameter are multiplied together to obtain the fuel contribution value of that parameter. The arithmetic mean of the fuel contribution values ​​of all parameters is then calculated to obtain the fuel availability of the steam boiler in the current optimization cycle.

[0103] It should be noted that the relative change is a dimensionless parameter dynamic fluctuation index, which can objectively reflect the magnitude of parameter change compared to normal operating conditions; the air supply synchronization coefficient is used to quantify the degree of temporal synchronization between parameter combustion response and air supply adjustment action; the fuel synchronization coefficient is used to quantify the degree of temporal synchronization between parameter combustion response and fuel adjustment action; the air supply arrival degree is used to comprehensively characterize the actual sufficiency and effectiveness matching level of the air supply adjustment command after it acts on the furnace combustion interface; the fuel arrival degree is used to comprehensively characterize the actual sufficiency and effectiveness matching level of the fuel adjustment command after it acts on the furnace combustion interface.

[0104] In some embodiments, the air supply level and the fuel supply level are proportioned in combination with the target air-fuel ratio to generate the air-fuel ratio deviation, which can be achieved in the following ways:

[0105] Obtain the dynamic characteristic parameters of the boiler combustion system;

[0106] The ideal air-fuel ratio is determined based on the target air-fuel ratio corresponding to the current optimization cycle and the dynamic characteristic parameters.

[0107] The air supply level is mapped to the fuel supply level to obtain the actual air-fuel ratio, and then the air-fuel ratio deviation of the actual air-fuel ratio relative to the ideal air-fuel ratio is determined.

[0108] The air-fuel ratio deviation is subjected to dead-zone filtering and amplitude limiting to obtain the air-fuel ratio deviation.

[0109] It should be noted that the dynamic characteristic parameters are used to characterize the dynamic response characteristics of the boiler combustion system under the current operating conditions; the target air-fuel ratio is dynamically set in combination with boiler load command, coal quality characteristics, and environmental conditions, and is the expected optimal ratio of air supply and fuel quantity under the current operating conditions. Its value can be reasonably adjusted around the theoretical air-fuel ratio. The theoretical air-fuel ratio is calculated based on the chemical composition of the fuel and is a fixed ratio of the minimum air quantity and fuel quantity required for complete combustion of the fuel. This ratio is determined only by the fuel quality and does not change with the operating conditions; the ideal air-fuel ratio is the optimal air-fuel ratio obtained by further correction based on the target air-fuel ratio and combined with the real-time dynamic operating conditions of the boiler. It is used to define the standard matching relationship between the air supply and fuel supply under the current operating conditions; the air-fuel ratio deviation is the difference between the actual air-fuel ratio and the ideal air-fuel ratio after filtering and amplitude limiting. It is used to quantify the deviation between the actual air-fuel ratio and the optimal ratio. When the deviation is positive, it means that the furnace air supply is relatively abundant and the oxygen content of the flue gas is relatively high; when the deviation is negative, it means that the furnace air supply is relatively insufficient and the oxygen content of the flue gas is relatively low.

[0110] In practice, firstly, the target air-fuel ratio corresponding to the current optimization cycle is obtained from the boiler control system, while dynamic characteristic parameters such as boiler load, fuel quality, air supply system response time, and fuel delivery response time are collected. Secondly, since the boiler combustion process is generally affected by dynamic factors such as air supply response lag, fuel delivery inertia, and fuel quality fluctuations, the target air-fuel ratio is corrected using the aforementioned dynamic characteristic parameters to obtain an ideal air-fuel ratio that adapts to the actual operating conditions of the current optimization cycle. Specifically, the weight coefficients of each dynamic characteristic parameter are determined using the analytic hierarchy process (AHP), and all dynamic characteristic parameters are normalized to obtain dimensionless operating condition deviation factors. The operating condition deviation factors of each dynamic characteristic parameter are multiplied by their corresponding weights and then summed to obtain the comprehensive operating condition deviation. The comprehensive correction coefficient is then calculated according to "1 + adjustment amplitude coefficient × comprehensive operating condition deviation," where the adjustment amplitude coefficient is statistically calibrated based on historical best operating condition data. Finally, the target air-fuel ratio is multiplied by the comprehensive correction coefficient to obtain the ideal air-fuel ratio that adapts to the current operating conditions.

[0111] In addition, in specific implementation, the actual air-fuel ratio under the current operating condition is obtained based on the mapping between the air supply level and the fuel supply level. The calculation method is to multiply the ratio of the air supply level to the fuel supply level by a reference air-fuel ratio conversion factor, wherein the reference air-fuel ratio conversion factor adopts the relevant reference value of the theoretical air-fuel ratio calibrated by the boiler manufacturer. In order to avoid calculation anomalies caused by the denominator approaching zero, when the fuel supply level is close to zero, the actual air-fuel ratio is directly assigned to a preset upper limit threshold. This upper limit threshold is set according to the maximum air-fuel ratio specified in the boiler safety operation procedure. The difference between the actual air-fuel ratio and the ideal air-fuel ratio is calculated as the air-fuel ratio deviation. Finally, the dead zone threshold and amplitude limiting range corresponding to the air-fuel ratio deviation are pre-configured. The dead zone threshold is pre-calibrated in conjunction with the normal measurement noise level of the air-fuel ratio deviation, and the amplitude limiting range is determined based on the boiler's safe operation boundary. The judgment rule is as follows: when the absolute value of the air-fuel ratio deviation is less than the dead zone threshold, the deviation is determined to be caused by a small disturbance, is an invalid deviation, and is set to zero; otherwise, the current deviation is retained as a valid deviation. Subsequently, the effective deviation after filtering is subjected to amplitude limiting constraint to limit the value within the preset amplitude limiting range. If it exceeds the range, the corresponding boundary value is truncated, and finally the air-fuel ratio deviation is obtained.

[0112] It should be noted that integrating the relative change and the synchronization coefficient in the calculation can comprehensively reflect the dual characteristics of each parameter in the amplitude and time domains; by solving the air supply and fuel supply levels through multi-parameter weighted integration, the influence of on-site noise interference on a single parameter can be reduced; relying on dynamic characteristic parameters to dynamically correct the target air-fuel ratio can adaptively cope with complex operating conditions such as load fluctuations and coal quality changes, improving the adaptability of air-fuel ratio calculation; combined with dead zone filtering and amplitude limiting processing, frequent system adjustments caused by small disturbances can be avoided, effectively improving the operational stability of the boiler combustion control system.

[0113] In step S104, based on the air-fuel timing deviation and the air-fuel ratio deviation, the set air supply volume and set fuel quantity for the next optimization cycle are corrected, and an optimization control command is generated and sent to the boiler combustion execution unit according to the corrected set air supply volume and set fuel quantity.

[0114] In some embodiments, the correction of the set air supply volume and set fuel quantity for the next optimization cycle based on the air-fuel timing deviation and the air-fuel ratio deviation can be achieved in the following ways:

[0115] The wind coal timing deviation and the wind coal ratio deviation are respectively subjected to direction-amplitude normalization to obtain the wind coal timing compensation amount and the wind coal ratio compensation amount.

[0116] Based on the wind-coal timing compensation amount, the air supply timing correction component and the fuel timing correction component are determined according to the preset timing correction rules. Based on the wind-coal ratio compensation amount, the air supply ratio correction component and the fuel ratio correction component are determined according to the preset ratio correction rules.

[0117] Adaptive fusion processing is performed on the air supply timing correction component and the air supply ratio correction component to obtain the air supply correction amount; adaptive fusion processing is performed on the fuel timing correction component and the fuel ratio correction component to obtain the fuel correction amount.

[0118] The air supply volume correction is used to limit the adjustment of the basic air supply volume for the next optimization cycle to obtain the set air supply volume. The fuel quantity correction is used to limit the adjustment of the basic fuel quantity for the next optimization cycle to obtain the set fuel quantity.

[0119] It should be noted that the preset timing correction rule and the preset ratio correction rule can be pre-established based on the boiler combustion mechanism, operating experience, historical optimization samples, and on-site calibration results. The two types of rules are used to output correction components with adjustment direction to correct the adjustment amount of air supply and fuel. Specifically, the preset timing correction rule is used to output directional timing correction components for the air supply side and the fuel side according to the sequential arrival relationship of air supply and fuel at the furnace combustion interface. For example, when the air-fuel timing deviation indicates that the air supply lags behind the fuel, the timing advance correction component on the air supply side is increased or the timing advance correction component on the fuel side is decreased according to the rule. The preset ratio correction rule is used to output directional ratio correction components for the air supply side and the fuel side according to the degree of deviation of the air-fuel ratio from the target air-fuel ratio. For example, when the air-fuel ratio deviation indicates that the current air volume is relatively high compared to the fuel volume, the ratio correction component on the air supply side is decreased or the ratio correction component on the fuel side is increased according to the rule.

[0120] In specific implementation, firstly, the sign of the air-coal timing deviation is extracted as the timing deviation direction, and its absolute value is extracted as the timing deviation amplitude. The timing deviation amplitude is then compared with a preset timing deviation calibration benchmark, and combined with the timing deviation direction, a directional air-coal timing compensation amount is obtained. Similarly, the proportioning deviation direction and proportioning deviation amplitude of the air-coal proportioning deviation are extracted, and the proportioning deviation amplitude is compared with a preset proportioning deviation calibration benchmark. Combined with the proportioning deviation direction, a directional air-coal proportioning compensation amount is obtained. The preset timing deviation calibration benchmark is calibrated based on the allowable air-coal arrival time difference under typical boiler load; the preset proportioning deviation calibration benchmark is calibrated based on historical stable combustion condition data. Then, based on the air-fuel timing compensation amount, the air supply timing correction component and the fuel timing correction component are determined according to the preset timing correction rules, so that the arrival time of air supply and fuel at the furnace combustion interface tends to be consistent in the next optimization cycle; at the same time, based on the air-fuel ratio compensation amount, the air supply ratio correction component and the fuel ratio correction component are determined according to the preset ratio correction rules, so that the ratio of air supply volume to fuel volume in the next optimization cycle tends to be close to the ideal air-fuel ratio.

[0121] In specific implementation, the air supply timing correction component and the air supply ratio correction component are adaptively fused to obtain the air supply correction amount. Specifically, the boiler operating conditions within the current optimization cycle are first identified and divided into steady-state conditions and dynamic load-changing conditions. In this application, the operating condition is determined by calculating the steam flow rate change rate per unit time: if the steam flow rate change rate is lower than a preset load fluctuation judgment threshold, such as 3% of the rated load per minute, it is determined to be a steady-state operating condition; otherwise, it is determined to be a dynamic load-changing condition. The weights of the two types of components are dynamically allocated according to the operating condition type, and the air supply correction is calculated using a dual-component linear weighted fusion method. The quantities and weights of each component satisfy normalization constraints. The specific weight allocation rules are as follows: Under steady-state conditions, the supply air ratio correction component is set as the main weight, and the supply air timing correction component is set as the auxiliary weight; under dynamic load conditions, the supply air timing correction component is set as the main weight, and the supply air ratio correction component is set as the auxiliary weight; when the two types of correction components adjust in opposite directions, their weights are set to equal proportions, and the direction of the final generated supply air correction is consistent with the component with the larger amplitude among the two types of correction components; similarly, the same adaptive fusion logic is applied to the fuel timing correction component and the fuel ratio correction component to obtain the fuel correction quantity.

[0122] In addition, in specific implementation, the basic air supply volume and basic fuel quantity corresponding to the next optimization cycle are obtained from the boiler coordination control system; the corresponding basic air supply volume and basic fuel quantity are superimposed and corrected by the air supply correction amount and fuel correction amount respectively, and the correction results are subject to amplitude limit constraints, so as to finally obtain the set air supply volume and set fuel quantity for the next optimization cycle. The upper and lower limit parameters of the amplitude limit constraint are pre-calibrated based on the rated design parameters of the boiler.

[0123] It should be noted that by combining the timing deviation of air and coal with the ratio deviation to correct the air volume and fuel quantity, and by introducing direction-amplitude normalization, adaptive weight fusion and amplitude limit safety constraints, the system can not only ensure accurate compensation for the air-coal mismatch problem, but also take into account the response priority and operational safety under different operating conditions, thereby improving the overall robustness of boiler combustion energy-saving optimization control.

[0124] In practice, the set air volume and set fuel quantity are converted into instruction forms that can be recognized by the air supply actuator and the fuel actuator, respectively, such as damper opening and coal feeder speed. Before the instruction is issued, the execution authority, operating boundary and safety interlock verification are completed in sequence. If the verification is successful, the instruction is sent to the distributed control system to drive the corresponding actuator to operate according to the set target. If the verification fails, the instruction is prohibited from being issued, or the instruction of the previous cycle remains unchanged. This ensures that the corrected set air volume and set fuel quantity are issued to the actuator in the form of compliant instructions to participate in boiler combustion control, intercept instructions that exceed limits and violate safety constraints, and thus improve the operational reliability of the energy-saving optimization control of the steam boiler.

[0125] Therefore, this application demonstrates that, firstly, by calculating the total response delay between the change characteristic moment and the retrospective baseline adjustment term issuance moment, and combining this with the channel pre-deployment delay to obtain the comprehensive response delay, it is possible to distinguish the time lag of different stages, making the delay analysis more consistent with the actual physical mechanism of the boiler combustion process. Based on the comprehensive response delay, the key sampling moments of each parameter are retrospectively analyzed to obtain the combustion effectiveness moment of each parameter at the furnace combustion interface. This allows the sampling moments obtained from external monitoring to be corrected to the actual effective time of the regulating medium in the combustion zone, improving the accuracy and stability of steam boiler combustion status monitoring and energy-saving optimization control. Secondly, by using the combustion effectiveness moment of each parameter as a candidate moment, and integrating multiple types of response sensitivity coefficients and time-series reliability coefficients to construct weights and achieve consistent fusion, the application avoids the random errors present in single-parameter judgments, ensuring that the air supply arrival moment and fuel arrival moment truly reflect the actual operating state of the furnace air and coal. Then, by solving for the air supply and fuel supply levels through multi-parameter weighted integration, the susceptibility of single parameters to on-site noise interference can be reduced. Dynamically correcting the target air-fuel ratio based on boiler dynamic characteristic parameters allows for adaptive adaptation to complex actual operating conditions such as load fluctuations and coal quality changes, improving the operating condition adaptability of the air-fuel ratio calculation. Combining dead-zone filtering and amplitude limiting processing avoids frequent system adjustments caused by small disturbances, effectively improving the operational stability of the boiler combustion control system. Finally, the air-fuel timing deviation and ratio deviation are jointly used to correct the air supply and fuel quantity, and direction-amplitude normalization, adaptive weight fusion, and amplitude limiting safety constraints are introduced. This ensures accurate compensation for air-fuel mismatch problems while also considering response priorities and operational safety under different operating conditions, improving the overall robustness of boiler combustion energy-saving optimization control.

[0126] In summary, the technical solution adopted in this application can combine the timing deviation of air and coal and the ratio deviation to synergistically correct the air supply volume and fuel quantity, thereby improving the combustion efficiency and energy-saving control level of the steam boiler.

[0127] In another aspect, in some embodiments, this application provides an energy-saving optimization system based on steam boiler combustion status monitoring, referencing... Figure 4 The figure is a schematic diagram of an energy-saving optimization system based on steam boiler combustion state monitoring, according to some embodiments of this application. The energy-saving optimization system based on steam boiler combustion state monitoring includes:

[0128] The timing backtracking module 201 is used to acquire the combustion state timing data of the steam boiler in the current optimization cycle, and to backtrack and map the key sampling times of each parameter in the combustion state timing data to obtain the combustion effective time of each parameter at the furnace combustion interface.

[0129] The deviation determination module 202 is used to determine the air supply arrival time and fuel arrival time based on the combustion activation time of each parameter, thereby obtaining the air-fuel timing deviation.

[0130] It should be noted that the deviation determination module 202 is also used to determine the degree of air supply and the degree of fuel supply based on the combustion activation time and state change amplitude of each parameter, and to combine the degree of air supply and the degree of fuel supply with the target air-fuel ratio to generate the air-fuel ratio deviation.

[0131] The energy-saving control module 203 is used to correct the set air volume and set fuel volume for the next optimization cycle based on the air-fuel timing deviation and the air-fuel ratio deviation, and generate an optimization control command based on the corrected set air volume and set fuel volume and send it to the boiler combustion execution unit.

[0132] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described energy-saving optimization method based on steam boiler combustion status monitoring.

[0133] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device implementing an energy-saving optimization method based on steam boiler combustion state monitoring, according to some embodiments of this application. The energy-saving optimization method based on steam boiler combustion state monitoring in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0134] The processor 301 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the energy-saving optimization method based on steam boiler combustion status monitoring in this application.

[0135] The communication bus 302 can be used to transmit information between the aforementioned components.

[0136] The memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0137] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the determination of the energy-saving optimization method based on steam boiler combustion status monitoring can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0138] Communication interface 304 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0139] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0140] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0141] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-mentioned energy-saving optimization method based on steam boiler combustion status monitoring.

[0142] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0143] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An energy-saving optimization method based on steam boiler combustion status monitoring, characterized in that, The steps include the following: Obtain the combustion state time-series data of the steam boiler in the current optimization cycle, and backtrack and map the key sampling times of each parameter in the combustion state time-series data to obtain the combustion effective time of each parameter at the furnace combustion interface. Based on the combustion activation time of each parameter, the air supply arrival time and fuel arrival time are determined, thereby obtaining the air-fuel timing deviation; Based on the combustion activation time and state change amplitude of each parameter, the degree of air supply and fuel supply are determined. The air supply and fuel supply are then matched with the target air-fuel ratio to generate the air-fuel ratio deviation. Based on the air-fuel timing deviation and the air-fuel ratio deviation, the set air supply volume and set fuel quantity for the next optimization cycle are corrected. An optimization control command is generated based on the corrected set air supply volume and set fuel quantity and sent to the boiler combustion execution unit.

2. The method as described in claim 1, characterized in that, By backtracking and mapping the key sampling times of each parameter in the combustion state time series data, the combustion activation time of each parameter at the furnace combustion interface is obtained, specifically including: Obtain adjustment instruction information within the current optimization cycle, the adjustment instruction information including air supply adjustment items and fuel adjustment items, and record the issuance time of the air supply adjustment items and the fuel adjustment items respectively; The change characteristic moments corresponding to each parameter are obtained from the combustion state time series data; Based on the response correlation between each parameter and the air supply adjustment item and the fuel adjustment item, determine the backtracking benchmark adjustment item corresponding to each parameter; Based on the issuance time of the backtracking benchmark adjustment term and the change characteristic time of the corresponding parameter, the comprehensive response delay corresponding to each parameter is determined; Based on the comprehensive response delay corresponding to each parameter, the key sampling time of each parameter is back-mapped to obtain the combustion effective time of each parameter at the furnace combustion interface.

3. The method as described in claim 2, characterized in that, The specific steps for obtaining the change characteristic moments corresponding to each parameter in the combustion state time series data include: Extract the time-series curves corresponding to each parameter from the combustion state time-series data and smooth the time-series curves to obtain the denoised parameter time-series curves. The parameter time series curve is dynamically differentially analyzed by a preset sliding time window to obtain the rate of change increment of the parameter time series curve. The moment when the rate of change increment reaches the preset increment threshold corresponding to the parameter is determined as the change characteristic moment of the parameter. By iterating through all parameters, the characteristic moments of change of each parameter in the combustion state time series data are obtained in turn.

4. The method as described in claim 1, characterized in that, Based on the combustion activation time of each parameter, the air supply arrival time and fuel arrival time are determined, thus obtaining the specific air-fuel timing deviation, including: Obtain the air supply response sensitivity coefficient of each parameter relative to the air supply channel, the fuel response sensitivity coefficient relative to the fuel channel, and the corresponding time series reliability coefficient under the current optimization cycle; The combustion activation time corresponding to each parameter is used as the candidate time. Feature correlation analysis is performed based on the air supply response sensitivity coefficient and the time series reliability coefficient to construct the air supply time series weight for each candidate moment, and the fuel time series weight corresponding to each candidate moment is determined according to the fuel response sensitivity coefficient and the time series reliability coefficient. Based on each candidate moment and its corresponding air supply timing weight, the air supply timing consistency fusion is performed to obtain the air supply arrival moment of the air supply channel. Fuel arrival times of the fuel channel are obtained by performing fuel time sequence consistency fusion based on each candidate time and its corresponding fuel time sequence weight. Based on the arrival time of the air supply and the arrival time of the fuel, the timing characteristics are calculated to generate the air-fuel timing deviation.

5. The method as described in claim 1, characterized in that, Based on the combustion activation time and state change amplitude of each parameter, the determination of the air supply level and fuel supply level specifically includes: Normalize the magnitude of the state change of each parameter to obtain the corresponding relative change; Based on the time proximity between the combustion activation time of each parameter and the air supply arrival time, the air supply synchronization coefficient corresponding to each parameter is determined. Based on the time proximity between the combustion activation time of each parameter and the fuel arrival time, the fuel synchronization coefficient corresponding to each parameter is determined; Based on the relative change of the same parameter, the air supply synchronization coefficient, and the air supply response sensitivity coefficient, a collaborative mapping is performed to obtain the air supply contribution value of the parameter. The air supply contribution values ​​of all parameters are integrated and processed to obtain the degree of air supply arrival. Based on the relative change of the same parameter, the fuel synchronization coefficient, and the fuel response sensitivity coefficient, a collaborative mapping is performed to obtain the fuel contribution value of the parameter. The fuel contribution values ​​of all parameters are then integrated to obtain the fuel availability.

6. The method as described in claim 1, characterized in that, The air-fuel ratio deviation is generated by combining the target air-fuel ratio with the air supply level and the fuel supply level. Specifically, it includes: Obtain the dynamic characteristic parameters of the boiler combustion system; The ideal air-fuel ratio is determined based on the target air-fuel ratio corresponding to the current optimization cycle and the dynamic characteristic parameters. The air supply level is mapped to the fuel supply level to obtain the actual air-fuel ratio, and then the air-fuel ratio deviation of the actual air-fuel ratio relative to the ideal air-fuel ratio is determined. The air-fuel ratio deviation is subjected to dead-zone filtering and amplitude limiting to obtain the air-fuel ratio deviation.

7. The method as described in claim 1, characterized in that, Based on the aforementioned air-fuel timing deviation and air-fuel ratio deviation, the correction of the set air supply volume and set fuel quantity for the next optimization cycle specifically includes: The wind coal timing deviation and the wind coal ratio deviation are respectively subjected to direction-amplitude normalization to obtain the wind coal timing compensation amount and the wind coal ratio compensation amount. Based on the wind-coal timing compensation amount, the air supply timing correction component and the fuel timing correction component are determined according to the preset timing correction rules. Based on the wind-coal ratio compensation amount, the air supply ratio correction component and the fuel ratio correction component are determined according to the preset ratio correction rules. Adaptive fusion processing is performed on the air supply timing correction component and the air supply ratio correction component to obtain the air supply correction amount; adaptive fusion processing is performed on the fuel timing correction component and the fuel ratio correction component to obtain the fuel correction amount. The air supply volume correction is used to limit the adjustment of the basic air supply volume for the next optimization cycle to obtain the set air supply volume. The fuel quantity correction is used to limit the adjustment of the basic fuel quantity for the next optimization cycle to obtain the set fuel quantity.

8. An energy-saving optimization system based on steam boiler combustion status monitoring, used to execute the energy-saving optimization method based on steam boiler combustion status monitoring as described in any one of claims 1 to 7, characterized in that, The automatic detection system includes: The time-series backtracking module is used to acquire the combustion state time-series data of the steam boiler in the current optimization cycle, and to backtrack and map the key sampling times of each parameter in the combustion state time-series data to obtain the combustion effective time of each parameter at the furnace combustion interface. The deviation determination module is used to determine the air supply arrival time and fuel arrival time based on the combustion activation time of each parameter, thereby obtaining the air-fuel timing deviation. The deviation determination module is also used to determine the degree of air supply and the degree of fuel supply based on the combustion activation time and state change amplitude of each parameter, and to combine the degree of air supply and the degree of fuel supply with the target air-fuel ratio to generate the air-fuel ratio deviation. The energy-saving control module is used to correct the set air volume and set fuel volume for the next optimization cycle based on the air-fuel timing deviation and the air-fuel ratio deviation, and to generate an optimization control command based on the corrected set air volume and set fuel volume and send it to the boiler combustion execution unit.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device performs the energy-saving optimization method based on steam boiler combustion status monitoring as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement the energy-saving optimization method based on steam boiler combustion status monitoring as described in any one of claims 1 to 7.

Images