Boiler Combustion Optimization Control Methods and Systems for Coal-fired Power Plants

Abstract

This application relates to the field of boiler combustion optimization technology, specifically to a boiler combustion optimization control method and system for coal-fired power plants. The method includes: determining the flue gas heat loss and incomplete fuel combustion loss of the boiler based on its operating parameters, as well as the emissions of nitrogen oxides, sulfur dioxide, and carbon monoxide; collecting the daily electricity load of the power supply area; determining the predicted electricity load for the current moment; constructing an objective function; and using a particle swarm optimization algorithm to solve the objective function to determine the optimal operating parameters for boiler combustion. The method further involves using the difference between the predicted electricity load for the current moment and its neighboring moments to adjust the inertia weights in the particle swarm optimization algorithm in real time. This improves the accuracy of boiler combustion optimization control.

Description

Technical Field

[0001] This application relates to the field of boiler combustion optimization technology, specifically to boiler combustion optimization control methods and systems for coal-fired power plants. Background Technology

[0002] With the continuous increase in energy consumption and increasingly stringent environmental protection requirements, coal-fired power plants face enormous challenges in improving energy efficiency and reducing pollution emissions. Key parameters in the combustion process within the boiler are directly related to improving combustion efficiency and reducing exhaust emissions. Controlling these key parameters during boiler combustion can improve combustion efficiency and achieve efficient power supply.

[0003] However, in real life, the electricity demand at different times can cause drastic changes in the load of power plant boiler equipment, which in turn affects the key parameters in the combustion process. This makes the boiler combustion efficiency a dynamic optimization problem. Traditional particle swarm optimization algorithm seeks the optimal solution based on the current state. In response to the series of chain effects brought about by changes in electricity demand, the response of power plant boilers is lagging. For example, during the upcoming peak electricity demand period, the boiler operates at a stable load. After entering the peak period, in order to meet the current electricity demand, the power plant boiler will directly enter ultra-high load operation. Particle swarm optimization algorithm is difficult to find the optimal solution of the current combustion efficiency parameters in real time, which in turn affects combustion efficiency and pollutant emissions. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide a boiler combustion optimization control method and system for coal-fired power plants, the specific technical solution of which is as follows:

[0005] In a first aspect, embodiments of this application provide a boiler combustion optimization control method for coal-fired power plants, the method comprising the following steps:

[0006] The boiler combustion operating parameters are used to determine the flue gas heat loss and incomplete fuel combustion loss, as well as the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions from boiler combustion.

[0007] Collect the electricity load of the power supply area where the boiler is burning at each time of day; based on the actual electricity load of the current time in the historical daily data, and the difference between the actual electricity load and the actual electricity load of the current time in the same day and the actual electricity load of the adjacent time, determine the predicted value of the electricity load at the current time.

[0008] The boiler combustion operating parameters are weighted using the current electricity load forecast. Based on the flue gas heat loss and incomplete fuel combustion loss determined by the weighted operating parameters, as well as the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions, an objective function is constructed.

[0009] The objective function is solved using the particle swarm optimization algorithm to determine the optimal operating parameters for boiler combustion. The inertia weights in the particle swarm optimization algorithm are adjusted in real time by using the difference between the predicted electricity load values ​​at the current time and those at nearby times.

[0010] In one embodiment, the method for determining the predicted electricity load at the current moment is as follows:

[0011] In the formula, This represents the predicted electricity load at time t. It represents the k-th nearest neighbor time before time t on the d-th day prior to the current time t. Let D be the actual electricity load at the k-th nearest neighbor time, D be the preset number of days before the current time t, and K be the preset number of nearest neighbor times before time t. The weight of the actual electricity load at the k-th nearest time is denoted as the first weight. The first weight is determined by the difference between the actual electricity load at the k-th nearest time and the predicted electricity load at the nearest time before the current time t.

[0012] In one embodiment, determining the first weight includes:

[0013] In the formula, Let be the power consumption deviation at the k-th nearest time, where , For the time before the current time t Forecasted electricity load at any given time;

[0014] The first weight is determined based on the electricity consumption deviation.

[0015] In one embodiment, the expression for the first weight is: .

[0016] In one embodiment, the construction of the objective function includes:

[0017] Combining the flue gas heat loss and the fuel incomplete combustion loss, the first function is determined as follows: ,in, Let X be the first function, and X be the current operating parameters of the boiler combustion. The flue gas heat loss caused by the current operating parameters of boiler combustion. The loss of fuel due to incomplete combustion caused by the current operating parameters of the boiler combustion;

[0018] Based on the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions from boiler combustion, the second function is determined as follows: In the formula, For the second function, The nitrogen oxide emissions caused by the current operating parameters of the boiler combustion. The sulfur dioxide emissions are caused by the current operating parameters of the boiler combustion. The carbon monoxide emissions are caused by the current operating parameters of the boiler combustion. a, b, and c are the preset weights of nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions, respectively, where a+b+c=1.

[0019] By combining the first function and the second function, the target function is determined.

[0020] In one embodiment, the expression for the objective function is:

[0021] In the formula, Let be the objective function at time t. For the first function, For the second function, The weight of the boiler combustion operating parameters is denoted as the second weight, which is determined by the difference between the current time and the predicted electricity load value at the previous time.

[0022] In one embodiment, determining the second weight includes:

[0023] Calculate the difference between the current time and the predicted electricity load value of the previous time, and record it as the first difference. Use the negative of the first difference as the exponent of an exponential function with the natural constant as the base, and use the calculation result of the exponential function as the second weight.

[0024] In one embodiment, the inertia weights in the real-time modified particle swarm optimization algorithm include:

[0025] The maximum and minimum values ​​of the preset inertia weight are set, the difference between the maximum and minimum values ​​is calculated and recorded as the second difference, and the difference between the maximum and minimum predicted power load values ​​in all previous times is determined and recorded as the third difference.

[0026] By combining the first difference, the second difference, the third difference, and the minimum value of the preset inertia weight, the inertia weight in the particle swarm optimization algorithm at the current moment is determined.

[0027] In one embodiment, determining the inertia weights in the particle swarm optimization algorithm at the current moment includes:

[0028] Calculate the sum of the third difference and a preset value greater than 0, determine the ratio of the absolute value of the first difference to the sum, and calculate the product of the second difference and the ratio;

[0029] The inertia weight in the particle swarm optimization algorithm at the current moment is the sum of the product of the minimum preset inertia weight and the preset inertia weight.

[0030] Secondly, embodiments of this application also provide a boiler combustion optimization control system for a coal-fired power plant, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0031] This application has at least the following beneficial effects:

[0032] This application determines the flue gas heat loss and incomplete fuel combustion loss of boilers based on operating parameters of boiler combustion. These are used as control factors for boiler combustion optimization, helping to precisely optimize the boiler combustion process, improve combustion efficiency, and reduce energy waste. Furthermore, by effectively controlling the emissions of nitrogen oxides, sulfur dioxide, and carbon monoxide, environmental pollution is reduced, improving the environmental protection level of boiler combustion. Moreover, by utilizing historical electricity load data and load differences between adjacent time periods to predict the current electricity load, the accuracy of electricity load prediction is improved, thereby making boiler operation more stable and reducing boiler instability caused by load fluctuations. Risk; Finally, by constructing an objective function and using the particle swarm optimization algorithm, the optimal operating parameters for boiler combustion are obtained. This allows for adjustments to fuel supply, air distribution, and burner operation, ensuring the boiler maintains high combustion efficiency and low emissions under different loads. This avoids resource waste and pollution emissions caused by drastic load changes due to the lag in power plant boiler power supply response. Furthermore, by real-time correction of the inertia weights in the particle swarm optimization algorithm, the efficiency and accuracy of optimal operating parameter solving are improved, enabling refined control of the boiler combustion process, reducing boiler combustion instability, and enhancing the safety and reliability of boiler operation. Attached Figure Description

[0033] To more clearly illustrate the technical solutions and advantages 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 some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 A flowchart illustrating the steps of a boiler combustion optimization control method for a coal-fired power plant, provided as an embodiment of this application;

[0035] Figure 2 A flowchart is provided to construct the objective function for the particle swarm optimization algorithm. Detailed Implementation

[0036] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the boiler combustion optimization control method and system for coal-fired power plants proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0038] The following description, in conjunction with the accompanying drawings, details the specific scheme of the boiler combustion optimization control method and system for coal-fired power plants provided in this application.

[0039] Please see Figure 1 The diagram illustrates a flowchart of a boiler combustion optimization control method for a coal-fired power plant according to an embodiment of this application. The method includes the following steps:

[0040] S1, based on the boiler combustion operating parameters, determines the flue gas heat loss and incomplete fuel combustion loss of the boiler combustion, as well as the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions of the boiler combustion.

[0041] During the operation of a coal-fired power plant boiler, various operating parameters of the boiler are acquired through sensors on the boiler equipment, including boiler load, air-coal ratio, combustion temperature, pressure, oxygen concentration, flue gas composition, coal feed rate, primary air volume, secondary air volume, and excess air coefficient.

[0042] Existing boiler combustion optimization methods construct the objective function of boiler combustion using intelligent optimization algorithms, and solve for the optimal boiler combustion state by adjusting various operating parameters. In reality, electricity demand at different times leads to changes in the load of power plant boiler equipment, which in turn affects the operating parameters during the combustion process, making boiler combustion efficiency a dynamic optimization problem. Traditional optimization algorithms seek the optimal solution based on the current state, and in response to the series of cascading effects brought about by changes in electricity demand, the power plant boiler's response exhibits a lag.

[0043] To address the aforementioned issues, this application models the boiler combustion optimization problem under different electricity consumption periods using a particle swarm optimization algorithm improved based on dynamic time-varying prediction constraints. An objective function is constructed for each operating parameter, and the objective function for boiler combustion is designed by using the predicted electricity demand at future moments as an additional constraint. Furthermore, time-varying dynamic weights are designed based on the changes in the predicted electricity demand, enhancing the particle swarm optimization algorithm's ability to search for the optimal solution. This avoids resource waste and pollution emissions caused by drastic changes in boiler load due to the lag in the power plant's boiler power supply response.

[0044] Specifically, the boiler combustion optimization problem under different electricity consumption periods is transformed into a multi-objective optimization problem, which requires optimizing both combustion efficiency and exhaust emissions by combining various operating parameters of boiler combustion. Let the solution vector to be obtained by the particle swarm optimization algorithm in this embodiment be... This includes n operating parameters for boiler combustion. This indicates the first operating parameter for boiler combustion. This indicates the second operating parameter for boiler combustion. This represents the nth operating parameter of the boiler combustion.

[0045] First, consider the combustion efficiency of the boiler. Boiler combustion efficiency measures the amount of heat energy converted by the combustion system. The operating parameters of the boiler combustion collectively determine whether the fuel is completely burned and the effective utilization of the heat energy released during combustion. Combining the flue gas heat loss and the incomplete combustion loss of fuel, we construct the first function, with the following expression:

[0046] ,in, Let X be the first function, and X be the current operating parameters of the boiler combustion. The flue gas heat loss caused by the current operating parameters of boiler combustion. This refers to the loss due to incomplete combustion of fuel caused by the current operating parameters of the boiler. The calculation of flue gas heat loss and incomplete combustion of fuel loss is based on existing well-known techniques, and the specific process will not be elaborated here.

[0047] Secondly, the issue of boiler combustion exhaust emissions needs to be considered. Boiler exhaust emissions mainly depend on factors such as fuel characteristics, combustion temperature, excess air coefficient, air-to-coal ratio, and the completeness of pulverized coal combustion. These factors collectively influence the formation and emission concentration of pollutants in the flue gas, especially... The formation of [something] is highly sensitive to furnace temperature and oxygen concentration. Emissions are closely related to the sulfur content in coal and combustion conditions, while Emissions largely reflect incomplete combustion. By rationally optimizing the combustion process, the emissions of harmful gases and soot can be effectively reduced, meeting environmental protection requirements. A second function can be constructed, with the specific expression as follows:

[0048] In the formula, For the second function, The nitrogen oxide emissions caused by the current operating parameters of the boiler combustion. The sulfur dioxide emissions are caused by the current operating parameters of the boiler combustion. The carbon monoxide emissions are denoted by a, b, and c, representing the current operating parameters of the boiler combustion. Preset weights for nitrogen oxides (NOx), sulfur dioxide (SO2), and carbon monoxide (CO) emissions are given, respectively, where a + b + c = 1. In this embodiment, a = 0.55, b = 0.3, and c = 0.15. Implementers can set these values ​​according to actual conditions; this embodiment does not impose any restrictions. The calculation of NOx, SO2, and CO emissions is based on existing known techniques, and the specific process will not be elaborated upon.

[0049] S2, collect the electricity load of the power supply area where the boiler is burning at each time of day; based on the actual electricity load of the current time in the historical daily data, and the difference between the actual electricity load and the actual electricity load of the adjacent times of the current time in the same day, determine the predicted value of the electricity load at the current time.

[0050] In coal-fired power plants, boiler load is a core parameter that is dynamically adjusted based on the electricity demand of the power grid. In the comprehensive load curve of the power system, the electricity load exhibits different changes at different times, which can be divided into peak load, off-peak load, mid-load, and base load. Each load segment reflects the demand for electricity. Peak load represents the period when the electricity demand of the power system is at its highest, and the boilers of coal-fired power plants need to increase their operating load to meet high power output. During off-peak periods, the electricity demand drops to its lowest level of the day, and the boiler operating load needs to decrease accordingly to avoid energy waste. During mid-load and base load periods, the electricity demand is stable or the load fluctuation is small, and the boiler needs to maintain a stable load operation.

[0051] Based on the above analysis, this embodiment collects the daily electricity load of the power supply area where the boiler is burning at various times. The data is collected over a day, with a time interval of 15 minutes between adjacent times. The daily electricity load curve of the power supply area is plotted based on the collected electricity load, which facilitates the subsequent analysis and prediction of the daily electricity consumption of the power supply area. The implementer can limit the sampling time interval according to the actual situation. This embodiment does not impose any restrictions on this.

[0052] Because changes in electricity demand determine changes in boiler load, boilers need to adjust their operating parameters according to these changes to maintain optimal combustion efficiency and exhaust emissions. Therefore, based on current and past data... Historical electricity load data from the past 24 days is used to construct dynamic prediction constraints. , used to indicate the current Forecasted electricity load at any given time. The specific expression is:

[0053] In the formula, This represents the predicted electricity load at time t. It represents the k-th nearest neighbor time before time t on the d-th day prior to the current time t. Let D be the actual electricity load at the k-th nearest neighbor time, D be the preset number of days before the current time t, and K be the preset number of nearest neighbor times before time t. The weight of the actual electricity load at the k-th nearest time is denoted as the first weight. The first weight is determined by the difference between the actual electricity load at the k-th nearest time and the predicted electricity load at the nearest time before the current time t.

[0054] It should be noted that in this embodiment, D=30, the unit is days, K=5, and there is no unit. When k=0, it means the time t of the dth day before the current time t. The implementer can set the values ​​of D and K according to the actual situation. This embodiment does not restrict them.

[0055] The first weight is calculated as follows:

[0056] In the formula, Let be the power consumption deviation at the k-th nearest time, where , For the time before the current time t The predicted electricity load at any given time. The expression for the first weight is: .

[0057] It should be understood that when Historical electricity load data of the nearest neighbor time. and A large discrepancy indicates that the historical electricity load data... If the error between the predicted load and the actual load is large, then The smaller, the more... Weighting in electricity load forecasting The smaller; conversely, and When the difference is small, it indicates that the historical electricity load data The error with the predicted load is small. The larger, the more it means Weighting in electricity load forecasting The larger the value, the greater the dynamic prediction constraint. This design assigns prediction weights to the actual load values ​​at each historical moment and its nearest neighbor within a short period of time during prediction. Using power load forecast results is more accurate. Specifically, when... At this time, the boiler is in the start-up state and does not need to be optimized to constrain the boiler combustion parameters by predicting electricity demand. .

[0058] S3. The boiler combustion operating parameters are weighted using the current electricity load forecast value. Based on the flue gas heat loss and incomplete fuel combustion loss determined by the weighted operating parameters, as well as the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions, an objective function is constructed.

[0059] During the operation of a coal-fired power plant, fluctuations in the power grid's demand directly affect the boiler's combustion status. During peak electricity demand periods, the load surges dramatically in a short time. To meet this massive instantaneous power demand, the boiler operates at high load, increasing the coal and air feed rates. However, coal-fired boilers are constrained by the physicochemical characteristics of the combustion process; after pulverized coal enters the furnace, it requires a certain amount of time to be heated and fully combusted. A sudden and significant increase in the coal feed rate leads to incomplete combustion of the pulverized coal, resulting in lower-than-expected oxygen consumption within the boiler. In this high-temperature, high-oxygen environment, excessive oxygen is produced. , Pollutants such as flue gas are generated, and some heat is not effectively utilized, resulting in increased heat loss in flue gas and decreased boiler combustion efficiency.

[0060] During off-peak electricity demand, power consumption drops significantly. At this time, the boiler's target load should be adjusted accordingly, requiring a reduction in both coal and air feed, which should consequently lower the furnace temperature. However, due to the significant thermal inertia of boiler combustion, the furnace temperature, pressure, and flue gas flow cannot decrease dramatically instantaneously. If the boiler immediately adjusts its parameters based on the instantaneous load condition, rapidly reducing the coal and air feed, it may cause an excessively sudden drop in furnace temperature, leading to unstable combustion, increased CO emissions, and even the risk of flameout. Failure to predict and adjust in advance can easily result in fuel waste and reduced combustion efficiency.

[0061] Therefore, in order to avoid a series of combustion problems caused by changes in electricity load, load trend changes can be identified in advance by predicting electricity load, and parameters such as coal feed and air feed can be gradually adjusted to ensure a smooth transition in the boiler combustion process, thereby ensuring that combustion efficiency and exhaust emission indicators are at their optimal levels.

[0062] Based on the above and dynamic prediction constraints The objective function for boiler combustion is:

[0063] ;

[0064] ;

[0065] In the formula, The weights of the boiler combustion operating parameters are denoted as the second weight, and e is the natural constant. This represents the predicted electricity load at time t. This represents the predicted electricity load value from the previous time point at the current time t. Let be the objective function at time t. For the first function, This is the second function. This is denoted as the first difference. The flowchart for constructing the objective function of the particle swarm optimization algorithm is as follows: Figure 2 As shown.

[0066] The objective function constructed in this embodiment uses the running parameter vector. Using the predicted electricity load at different times as input, and combustion efficiency... Maximize exhaust emissions The objective is to minimize the constraint terms using dynamic prediction. and When the difference is used as an additional constraint to control changes in boiler decision variables and to compensate for boiler load changes caused by drastic fluctuations in electricity consumption, the boiler's response lag prevents operating parameters from achieving optimal boiler combustion. At that time, it indicates that in The operating parameters before adding dynamic prediction constraints are affected by a sudden increase in power demand. It is difficult to meet the optimal combustion control when the boiler load suddenly increases. The aim is to pre-increase the values ​​of operating parameters to meet the demands of high-load boiler combustion and optimize combustion under high load, avoiding the difficulty in adjusting and controlling the parameters of the current optimal boiler combustion due to response lag when electricity demand and boiler load suddenly increase; when At that time, electricity demand decreases. Adjusting boiler operating parameters in advance can prevent incomplete combustion of fuel caused by sudden reductions in boiler operating parameters, which can lead to decreased combustion efficiency and increased exhaust emissions.

[0067] This completes the construction of the mathematical model for the optimized control of boiler combustion.

[0068] S4. Using the particle swarm optimization algorithm, the objective function is solved to determine the optimal operating parameters for boiler combustion. The inertia weight in the particle swarm optimization algorithm is adjusted in real time by using the difference between the predicted electricity load at the current time and the time in the vicinity.

[0069] The objective function at time t is solved using the particle swarm optimization algorithm to maximize the objective function. In the initialization of the operating parameters in the solution vector X and in each subsequent iteration, it is ensured that the values ​​of the operating parameters in the solution vector X are within their normal range, that is, to avoid the occurrence of meaningless boiler combustion operating parameters.

[0070] Traditional particle swarm optimization algorithms are mostly static optimization algorithms, which only solve for the optimal parameter combination under fixed operating conditions. However, when external environmental factors such as electricity demand change abruptly, such as during an upcoming peak period when electricity demand rises sharply, the boiler's thermal inertia and the lag in the combustion process mean that the optimal parameters at that moment may not be suitable for conditions where the load increases significantly in a short period of time. This can lead to large errors, resulting in an inability to respond to system changes in a timely manner, ultimately causing reduced combustion efficiency and excessive exhaust emissions.

[0071] To address the aforementioned issues, this embodiment introduces time-varying adaptive inertia weights to update particle velocities during the particle swarm optimization algorithm solution process. Specifically, the current time-to-date electricity demand prediction constraint is used. Introduced into the optimization algorithm, the inertia weight of particle updates in the particle swarm optimization algorithm is dynamically adjusted by predicting the changes in electricity demand during upcoming peak or off-peak periods. The inertia weight is adaptively adjusted as electricity demand changes.

[0072] Based on the above analysis, the inertia weight in the particle swarm optimization algorithm at the current moment... The expression is:

[0073] In the formula, The preset maximum value of inertia weight, In this embodiment, the preset minimum inertia weight is used. , The implementer can set it according to the actual situation, and this embodiment does not impose any restrictions on it. This represents the predicted electricity load at time t. This represents the predicted electricity load value from the previous time point at the current time t. It is the maximum value of the predicted electricity load over all time periods prior to the current time. It is the minimum value of the predicted electricity load over all previous time periods. To ensure that the value is greater than 0 and to avoid a denominator of 0, this embodiment... The implementer can set it according to the actual situation; this embodiment does not impose any restrictions on this. This is denoted as the second difference. This is denoted as the third difference.

[0074] The time-varying dynamic weight design based on dynamic prediction constraints will adjust the electricity demand forecast value. A weight update mechanism is introduced to adjust the inertial weights in real time according to the trend of the predicted electricity load. If there is a large difference between the predicted electricity demand at the current moment and that at the previous moment, it indicates that the electricity demand has changed significantly, and the optimal particle solution at the previous moment is no longer sufficient to meet the algorithm's requirements. In this case, the weights are adjusted accordingly. This will also increase and enhance the particle swarm optimization's exploration capabilities, helping the algorithm to proactively search for boiler parameters to cope with sudden changes in electricity demand, preventing reduced combustion efficiency and excessive emissions due to boiler response lag. Similarly, if the difference between the current time and the predicted electricity load from the previous time is small, it indicates that the electricity demand is changing steadily, and the current boiler operating state can meet the electricity demand. (Inertia weight) The corresponding reduction is used to search near the current solution, improving the efficiency of the search. Specifically, when the predicted electricity load for future time periods is the maximum and minimum value up to the current time period, ,at this time The ability of particles to explore solution space reaches its peak; when hour, The particle velocity update weight is minimized, and the current optimal solution is found near the optimal solution of the previous time step, thus improving search efficiency. This is achieved by pre-emptively updating the particle velocity. Predict real-time electricity demand and update accordingly. By analyzing the boiler operating parameters at all times, the combustion optimization control of the boiler under dynamic load conditions can be improved, and the physical characteristics of the boiler combustion system can be better matched.

[0075] Finally, the optimal operating parameters for the current boiler combustion are solved using the particle swarm optimization algorithm. These parameters are then used to adjust the fuel supply, air distribution, and burner operating status, ensuring that the boiler maintains high combustion efficiency and low emissions under different loads. This optimizes the boiler's operating status. The learning factor of the particle swarm optimization algorithm is crucial. Set to 2, particle swarm count Set to 50, number of iterations The value is set to 200. The particle swarm optimization algorithm is a well-known existing technology, and the specific process will not be described in detail.

[0076] Based on the same inventive concept as the above methods, embodiments of this application also provide a boiler combustion optimization control system for coal-fired power plants, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described boiler combustion optimization control methods for coal-fired power plants.

[0077] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0078] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0079] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for optimizing boiler combustion control in coal-fired power plants, characterized in that, The method includes the following steps: The boiler combustion operating parameters are used to determine the flue gas heat loss and incomplete fuel combustion loss, as well as the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions from boiler combustion. Collect the electricity load of the power supply area where the boiler is burning at each time of day; based on the actual electricity load of the current time in the historical daily data, and the difference between the actual electricity load and the actual electricity load of the current time in the same day and the actual electricity load of the adjacent time, determine the predicted value of the electricity load at the current time. The boiler combustion operating parameters are weighted using the current electricity load forecast. Based on the flue gas heat loss and incomplete fuel combustion loss determined by the weighted operating parameters, as well as the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions, an objective function is constructed. The objective function is solved using the particle swarm optimization algorithm to determine the optimal operating parameters for boiler combustion. The inertial weights in the particle swarm optimization algorithm are adjusted in real time by using the difference between the predicted electricity load at the current time and that at the nearest time. The method for determining the predicted electricity load at the current moment is as follows: In the formula, This represents the predicted electricity load at time t. It represents the k-th nearest neighbor time before time t on the d-th day prior to the current time t. Let D be the actual electricity load at the k-th nearest neighbor time, D be the preset number of days before the current time t, and K be the preset number of nearest neighbor times before time t. The weight of the actual electricity load at the k-th nearest time is denoted as the first weight. The first weight is determined by the difference between the actual electricity load at the k-th nearest time and the predicted electricity load at the nearest time before the current time t.

2. The boiler combustion optimization control method for coal-fired power plants as described in claim 1, characterized in that, The determination of the first weight includes: In the formula, Let be the power consumption deviation at the k-th nearest time, where , For the time before the current time t Forecasted electricity load at any given time; The first weight is determined based on the electricity consumption deviation.

3. The boiler combustion optimization control method for coal-fired power plants as described in claim 2, characterized in that, The expression for the first weight is: .

4. The boiler combustion optimization control method for coal-fired power plants as described in claim 1, characterized in that, The construction of the objective function includes: Combining the flue gas heat loss and the fuel incomplete combustion loss, the first function is determined as follows: ,in, Let X be the first function, and X be the current operating parameters of the boiler combustion. The flue gas heat loss caused by the current operating parameters of boiler combustion. The loss of fuel due to incomplete combustion caused by the current operating parameters of the boiler combustion; Based on the nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions from boiler combustion, the second function is determined as follows: In the formula, For the second function, The nitrogen oxide emissions caused by the current operating parameters of the boiler combustion. The sulfur dioxide emissions are caused by the current operating parameters of the boiler combustion. The carbon monoxide emissions are caused by the current operating parameters of the boiler combustion. a, b, and c are the preset weights of nitrogen oxide emissions, sulfur dioxide emissions, and carbon monoxide emissions, respectively, where a+b+c=1. By combining the first function and the second function, the target function is determined.

5. The boiler combustion optimization control method for coal-fired power plants as described in claim 4, characterized in that, The expression for the objective function is: In the formula, Let be the objective function at time t. For the first function, For the second function, The weight of the boiler combustion operating parameters is denoted as the second weight, which is determined by the difference between the current time and the predicted electricity load value at the previous time.

6. The boiler combustion optimization control method for coal-fired power plants as described in claim 5, characterized in that, The determination of the second weight includes: Calculate the difference between the current time and the predicted electricity load value of the previous time, and record it as the first difference. Use the negative of the first difference as the exponent of an exponential function with the natural constant as the base, and use the calculation result of the exponential function as the second weight.

7. The boiler combustion optimization control method for coal-fired power plants as described in claim 6, characterized in that, The inertia weights in the real-time corrected particle swarm optimization algorithm include: The maximum and minimum values ​​of the preset inertia weight are set, the difference between the maximum and minimum values ​​is calculated and recorded as the second difference, and the difference between the maximum and minimum predicted power load values ​​in all previous times is determined and recorded as the third difference. By combining the first difference, the second difference, the third difference, and the minimum value of the preset inertia weight, the inertia weight in the particle swarm optimization algorithm at the current moment is determined.

8. The boiler combustion optimization control method for coal-fired power plants as described in claim 7, characterized in that, Determining the inertia weights in the particle swarm optimization algorithm at the current moment includes: Calculate the sum of the third difference and a preset value greater than 0, determine the ratio of the absolute value of the first difference to the sum, and calculate the product of the second difference and the ratio; The inertia weight in the particle swarm optimization algorithm at the current moment is the sum of the product of the minimum preset inertia weight and the preset inertia weight.

9. A boiler combustion optimization control system for a coal-fired power plant, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-8.

Images