Method and system for determining quantity of boiler sludge blending based on coupled BP neural network

Abstract

The present application belongs to the field of boiler sludge blending combustion quantity calculation, and discloses a method and system for determining the boiler sludge blending combustion quantity based on a coupled BP neural network. The present application can avoid excessive local temperature and effectively reduce the high-temperature corrosion phenomenon caused by the tangential flame brushing the wall by precisely adjusting the sludge blending combustion quantity. The BP neural network model can predict the temperature field distribution under different blending combustion quantities, control the temperature within a safe range, and prolong the service life of the boiler. The present application optimizes the sludge blending combustion quantity based on the real-time model of the denitration and desulfurization system, so that the NOx and SO2 emissions are controlled below the critical value. Through the prediction and control of the emissions, the environmental protection standards are met while blending the sludge, and the emissions of pollutants are reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of boiler sludge blending combustion quantity calculation, and particularly relates to a method and system for determining a boiler sludge blending combustion quantity based on a coupled BP neural network. BACKGROUND

[0002] However, among the current sludge treatment methods, the boiler blending combustion method can fully utilize the organic components in the sludge, has a fast and complete treatment speed, and has the dual advantages of small modification investment and saved coal usage, and is an extremely advantageous treatment method.

[0003] However, the coal-fired boiler blending combustion may cause problems such as reduced boiler efficiency, increased NOx treatment capacity of the denitration system, increased SO2 treatment capacity of the desulfurization system, increased treatment capacity of the dust removal system, and toxic gases such as dioxin in the flue gas after treatment, which restrict the coal-fired boiler sludge blending combustion quantity. The maximum sludge blending combustion quantity in the past is obtained based on experience such as the size of the unit and the treatment capacity of the auxiliary system, which is blind and makes the actual maximum sludge blending combustion quantity much lower than the capacity that the coal-fired boiler can withstand.

[0004] Patent document CN113790456B provides a method and system for calculating the maximum sludge blending combustion quantity of a coal-fired boiler, which, based on the relevant parameters of the coal-fired boiler, coal mill, denitration system, desulfurization system, dust removal system, and wastewater system under typical load and the characteristics of the sludge, improves the maximum sludge blending combustion quantity under typical load to the greatest extent while ensuring the safe operation of the coal-fired boiler, and can correct the maximum sludge blending combustion quantity in real time according to the target power generation power and the actual power generation power of the coal-fired unit. However, the calculation method can only calculate the maximum sludge blending combustion quantity under typical load, design conditions, and coal quality, and cannot adapt to the current situation of stronger coal blending in power plants, which may result in overestimation of the maximum sludge blending combustion quantity under worse coal quality conditions.

[0005] Patent document CN115951012A provides a method for determining the maximum sludge blending combustion rate of a coal-fired boiler, which, based on theoretical calculation, gradually determines the maximum sludge blending combustion quantity by means of a blending combustion test method, with the working conditions of the coal mill, the working conditions of the boiler burner, the actual efficiency of the boiler, and the pollutant emissions as limiting conditions. However, the method still has the following shortcomings: 1. The method needs to be measured on site through a blending combustion test and needs to be measured multiple times under multiple conditions, and can only represent the coal quality and working conditions at that time, and the estimated maximum blending combustion quantity is not accurate. SUMMARY

[0006] The purpose of the present application is to overcome the problem of high-temperature corrosion of the furnace caused by the large tangential flame of the wall-type tangential boiler, and to provide a method and system for determining the boiler sludge blending combustion quantity based on a coupled BP neural network.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a method for determining the amount of boiler sludge blending based on a coupled BP neural network, comprising the following steps:

[0009] Obtain the detailed structure of the denitrification system and desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitrification system and desulfurization system;

[0010] Based on the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, a relevant model of different coal qualities in the furnace is established. The CFD simulation values ​​are introduced into the relevant model to simulate the furnace temperature field.

[0011] The detailed structure of the denitrification system is combined with the furnace temperature field to obtain the denitrification efficiency and NOx emission index under the three-dimensional model;

[0012] The detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization efficiency and SO2 emission index under the three-dimensional model;

[0013] Based on the denitrification efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion, and the maximum amount of regulated sludge mixed combustion corresponding to the NOx emission is obtained.

[0014] Based on the desulfurization efficiency and SO2 emission index under the three-dimensional model, the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion, and the maximum amount of regulated sludge mixed combustion corresponding to the SO2 emission is obtained.

[0015] The maximum blending amount of regulating sludge corresponding to NOx emission and the maximum blending amount of regulating sludge corresponding to SO2 emission are trained through BP neural network to obtain the maximum blending amount of boiler sludge.

[0016] A further improvement of the present invention is to obtain the detailed structure of the denitrification system and the desulfurization system in the boiler, and to establish a furnace grid model based on the detailed structure of the denitrification system and the desulfurization system. The specific method is as follows:

[0017] Obtain the reactor structure, injection system, catalyst arrangement and flue gas parameters in the denitration system as parameter information, obtain the absorption tower structure, spray system, filler characteristics and flue gas flow parameters in the desulfurization system as boundary information;

[0018] A three-dimensional geometric model is established according to the obtained parameter information, and meshing is performed, and the boundary information is input into the three-dimensional geometric model to obtain a meshed model of the furnace.

[0019] Further improvement of the present application is that, according to the meshed model of the furnace, combined with real-time data of the denitration system and the desulfurization system, a relevant model of different coal qualities in the furnace is established, and the CFD simulation numerical value is brought into the relevant model, and the specific method of simulating the furnace temperature field is as follows:

[0020] Obtain the combustion characteristic parameters of different coal qualities, and establish a preliminary combustion model according to the combustion characteristic parameters of different coal qualities by using thermodynamics and a combustion model;

[0021] The combustion characteristic parameters of different coal qualities are input into the meshed model of the furnace to simulate the combustion process of different coal qualities in the furnace.

[0022] After coupling the preliminary combustion model and the meshed model of the furnace, the CFD simulation is adopted to obtain the furnace temperature field.

[0023] Further improvement of the present application is that, combined with the detailed structure of the denitration system and the furnace temperature field, the specific method of obtaining the denitration removal efficiency and the NOx emission index under the three-dimensional model is as follows:

[0024] According to the furnace temperature field, the temperature distribution at different positions in the furnace is determined, combined with the combustion characteristics and the NOx generation rate of different coal qualities, the generation process and the concentration distribution of NOx in the furnace are simulated;

[0025] According to the generation process and the concentration distribution of NOx in the furnace, combined with the detailed structure of the denitration system, the injection process of the reducing agent in the furnace is simulated, the mixing and diffusion of the reducing agent in the flue gas are simulated by using the CFD, according to the reaction rate and the reduction characteristics of the reducing agent at each temperature layer, the NOx reduction efficiency of each injection point is calculated;

[0026] According to the NOx reduction efficiency of each injection point, the denitration efficiency of each injection point is obtained, and the denitration efficiency of each injection point is summarized to obtain the denitration removal efficiency and the NOx emission index under the three-dimensional model.

[0027] Further improvement of the present application is that, combined with the detailed structure of the desulfurization system and the furnace temperature field, the specific method of obtaining the desulfurization removal efficiency and the SO2 emission index under the three-dimensional model is as follows:

[0028] According to the furnace temperature field, determine the generation amount and concentration distribution of SO2 in the flue gas, analyze the generation amount and concentration distribution in the flue gas, and obtain the SO2 distribution data in the flue gas;

[0029] Based on the SO2 distribution data in the flue gas and the detailed structure of the desulfurization system, the contact and reaction process between SO2 and the absorbent is simulated through CFD to obtain the local desulfurization efficiency of each spray layer;

[0030] According to the local desulfurization efficiency of each spray layer, the desulfurization removal efficiency and SO2 emission index are summarized.

[0031] A further improvement of the present invention is that, based on the denitrification efficiency and NOx emission index under the three-dimensional model, a criterion for the minimum NOx emission of boiler denitrification and a critical criterion for NOx emission when increasing the amount of sludge mixed combustion are obtained. Different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion. The specific method for obtaining the maximum amount of sludge mixed combustion corresponding to the NOx emission is as follows:

[0032] Obtain the combustion characteristics of sludge and establish a preliminary co-combustion model based on the combustion characteristics of sludge;

[0033] Based on the preliminary co-combustion model, combined with the furnace temperature field and flue gas flow model, the NOx generation process under different sludge co-combustion ratios was simulated, and the NOx generation amount and concentration distribution under each co-combustion ratio were obtained;

[0034] According to the NOx generation and concentration distribution under various sludge co-combustion ratios and the reaction efficiency of the denitrification system, the final NOx emissions under various sludge co-combustion ratios were obtained.

[0035] A further improvement of the present invention is that, based on the desulfurization removal efficiency and SO2 emission index under the three-dimensional model, a criterion for the minimum SO2 emission of boiler desulfurization and a critical criterion for SO2 emission for increasing the amount of sludge mixed combustion are obtained. Different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission for increasing the amount of sludge mixed combustion. The specific method for obtaining the maximum amount of sludge mixed combustion corresponding to the SO2 emission is as follows:

[0036] Obtain the sulfur content and combustion characteristics of the sludge, obtain the release characteristics of sulfur in the furnace under different blending ratios, and establish a preliminary blending model;

[0037] Based on the preliminary co-combustion model, combined with the furnace temperature field and flue gas flow characteristics, a CFD model was used to simulate the SO2 generation process under different sludge co-combustion ratios, and the effects of different co-combustion amounts on the combustion temperature and SO2 generation rate were obtained.

[0038] According to the influence of different sludge blending ratios on combustion temperature and SO2 generation rate, combined with the efficiency model of the desulfurization system, the final SO2 emissions under different sludge blending ratios are calculated.

[0039] A further improvement of the present invention is that the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions are trained through a BP neural network. The specific method for obtaining the maximum blending amount of boiler sludge is as follows:

[0040] Obtain the maximum amount of regulated sludge blended combustion corresponding to NOx emissions and the maximum amount of regulated sludge blended combustion corresponding to SO2 emissions, and perform normalization and standardization processing;

[0041] A BP neural network model was constructed, and the maximum amount of regulated sludge blended combustion corresponding to NOx emissions and the maximum amount of regulated sludge blended combustion corresponding to SO2 emissions were used to train the BP neural network model to obtain the final BP neural network model;

[0042] The maximum blending amount of regulated sludge corresponding to the actual Ox emission and the maximum blending amount of regulated sludge corresponding to the SO2 emission are input into the final BP neural network model to obtain the maximum blending amount of boiler sludge.

[0043] In a second aspect, the present invention provides a system for determining the amount of boiler sludge blending based on a coupled BP neural network, comprising:

[0044] The furnace grid model building module is used to obtain the detailed structure of the denitrification system and desulfurization system in the boiler, and build the furnace grid model based on the detailed structure of the denitrification system and desulfurization system;

[0045] The furnace temperature field acquisition module is used to establish relevant models of different coal qualities in the furnace based on the furnace grid model and combined with the real-time data of the denitrification system and desulfurization system. The CFD simulation values ​​are then introduced into the relevant models to simulate the furnace temperature field.

[0046] The denitrification efficiency acquisition module is used to combine the detailed structure of the denitrification system with the furnace temperature field to obtain the denitrification removal efficiency and NOx emission index under the three-dimensional model;

[0047] The desulfurization efficiency acquisition module is used to combine the detailed structure of the desulfurization system with the furnace temperature field to obtain the desulfurization efficiency and SO2 emission index under the three-dimensional model;

[0048] The NOx blending amount module is used to obtain the criterion for the minimum NOx emission amount of boiler denitrification and the critical criterion for NOx emission amount by increasing the sludge blending amount based on the denitrification efficiency and NOx emission index under the three-dimensional model. The module compares the different temperatures of the boiler furnace with the criterion for the minimum NOx emission amount of boiler denitrification and the critical criterion for NOx emission amount by increasing the sludge blending amount to obtain the maximum regulated sludge blending amount corresponding to the NOx emission amount.

[0049] The SO2 blending amount module is used to obtain the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission by increasing the amount of sludge blending based on the desulfurization removal efficiency and SO2 emission index under the three-dimensional model. The module compares the different temperatures of the boiler furnace with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission by increasing the amount of sludge blending to obtain the maximum amount of regulated sludge blending corresponding to the SO2 emission.

[0050] The model processing module is used to train the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions through BP neural network to obtain the maximum blending amount of boiler sludge.

[0051] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of a method for determining the amount of boiler sludge blending based on a coupled BP neural network.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention precisely adjusts the sludge blending rate to avoid excessive local temperatures and effectively reduces high-temperature corrosion caused by tangential flame wall brushing. The BP neural network model can predict the temperature field distribution under different blending rates, controlling it within a safe temperature range and extending the service life of the boiler. The present invention optimizes the sludge blending rate based on real-time models of the denitrification and desulfurization systems, keeping NOx and SO2 emissions below critical values. By predicting and controlling emissions, sludge blending can be achieved while meeting environmental standards and reducing pollutant emissions. While ensuring safety and environmental protection, the present invention can increase the maximum sludge blending rate, thereby achieving greater sludge resource recycling and reducing fuel costs. This method of optimizing the blending rate not only improves combustion efficiency but also promotes the recycling and utilization of solid waste, helping to promote sustainable development. By coupling the denitrification and desulfurization systems with the furnace temperature field, the optimized sludge blending rate helps to form a more stable combustion temperature field and improve combustion efficiency. This optimization process can reduce coal consumption, reduce dependence on coal resources, and save fuel costs. In summary, the present invention can not only solve the high-temperature corrosion problem of wall-type tangential circle boilers, but also reduce pollutant emissions, increase the sludge blending amount and combustion efficiency, thereby achieving economical and environmentally friendly boiler operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of the present invention;

[0055] Figure 2 is a system diagram of the present invention;

[0056] Figure 3 This is a system diagram of Example 10. DETAILED DESCRIPTION

[0057] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0058] Example 1:

[0059] See also Figure 1 The method for determining the amount of boiler sludge blending based on the coupled BP neural network includes the following steps:

[0060] S1, obtain the detailed structure of the denitrification system and the desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitrification system and the desulfurization system.

[0061] S2, based on the furnace grid model, combined with the real-time data of the denitrification system and desulfurization system, establish the relevant models of different coal qualities in the furnace, bring the CFD simulation values ​​into the relevant models, and simulate the furnace temperature field.

[0062] S3, the detailed structure of the denitrification system is combined with the furnace temperature field to obtain the denitrification removal efficiency and NOx emission index under the three-dimensional model.

[0063] S4, combines the detailed structure of the desulfurization system with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model.

[0064] S5. According to the denitrification efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when the sludge blending amount is increased are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when the sludge blending amount is increased, and the maximum regulated sludge blending amount corresponding to the NOx emission is obtained.

[0065] S6. Based on the desulfurization removal efficiency and SO2 emission index under the three-dimensional model, the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the sludge blending amount are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the sludge blending amount, and the maximum regulated sludge blending amount corresponding to the SO2 emission is obtained.

[0066] S7, training the maximum blending amount of the regulated sludge corresponding to the NOx emission and the maximum blending amount of the regulated sludge corresponding to the SO2 emission through a BP neural network to obtain the maximum blending amount of the boiler sludge.

[0067] Example 2:

[0068] See also Figure 2 , the system for determining the amount of boiler sludge blending based on coupled BP neural network includes:

[0069] The furnace grid model building module is used to obtain the detailed structure of the denitrification system and desulfurization system in the boiler, and build the furnace grid model based on the detailed structure of the denitrification system and desulfurization system;

[0070] The furnace temperature field acquisition module is used to establish relevant models of different coal qualities in the furnace based on the furnace grid model and combined with the real-time data of the denitrification system and desulfurization system. The CFD simulation values ​​are then introduced into the relevant models to simulate the furnace temperature field.

[0071] The denitrification efficiency acquisition module is used to combine the detailed structure of the denitrification system with the furnace temperature field to obtain the denitrification removal efficiency and NOx emission index under the three-dimensional model;

[0072] The desulfurization efficiency acquisition module is used to combine the detailed structure of the desulfurization system with the furnace temperature field to obtain the desulfurization efficiency and SO2 emission index under the three-dimensional model;

[0073] The NOx blending amount module is used to obtain the criterion for the minimum NOx emission amount of boiler denitrification and the critical criterion for NOx emission amount by increasing the sludge blending amount based on the denitrification efficiency and NOx emission index under the three-dimensional model. The module compares the different temperatures of the boiler furnace with the criterion for the minimum NOx emission amount of boiler denitrification and the critical criterion for NOx emission amount by increasing the sludge blending amount to obtain the maximum regulated sludge blending amount corresponding to the NOx emission amount.

[0074] The SO2 blending amount module is used to obtain the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission by increasing the amount of sludge blending based on the desulfurization removal efficiency and SO2 emission index under the three-dimensional model. The module compares the different temperatures of the boiler furnace with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission by increasing the amount of sludge blending to obtain the maximum amount of regulated sludge blending corresponding to the SO2 emission.

[0075] The model processing module is used to train the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions through BP neural network to obtain the maximum blending amount of boiler sludge.

[0076] Example 3:

[0077] The detailed structure of the denitrification system and desulfurization system in the boiler is obtained, and the specific method for establishing the furnace grid model based on the detailed structure of the denitrification system and desulfurization system is as follows:

[0078] Comprehensively obtain detailed structural information of the denitrification and desulfurization systems, including the physical and chemical parameters of key components such as the reactor, injection system, catalyst, absorption tower, and spray system. This data provides an accurate foundation for subsequent model construction.

[0079] The collected detailed information is input into a 3D modeling tool to create a detailed geometric model and perform meshing. Boundary conditions such as flue gas flow rate and temperature are accurately set in the model to enable it to realistically simulate the operating environment of the denitrification and desulfurization systems.

[0080] After the model is initially established, its accuracy is verified by comparing it with the system's actual operating data or CFD simulation results. Based on these comparisons, the model parameters are optimized as necessary to ensure that the model can accurately predict the temperature field, efficiency, and pollutant emissions of the denitrification and desulfurization system, providing a reliable simulation foundation for subsequent analysis.

[0081] Example 4:

[0082] Based on the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, a relevant model of different coal qualities in the furnace is established. The CFD simulation values ​​are introduced into the relevant model to simulate the furnace temperature field. The specific method is as follows:

[0083] Key combustion parameters for different coal qualities are collected and analyzed, including volatile matter content, ash content, fixed carbon content, calorific value, and ignition temperature. These parameters directly influence the intensity and speed of the combustion reaction and, ultimately, the distribution of the furnace temperature field. Based on this data, a preliminary combustion model is developed using thermodynamic and combustion models to ensure that the model reflects the combustion behavior of different coal types, laying the foundation for subsequent furnace temperature field modeling.

[0084] Based on the preliminary combustion model, the combustion characteristic parameters of different coal qualities were imported into the furnace mesh model. The furnace interior was divided into a fine grid, and boundary conditions such as coal quality, air flow, and temperature were set at different grid locations to enable the model to accurately simulate the combustion process of different coal qualities within the furnace. This step enabled the combustion thermodynamic characteristics of different coal types to be reflected in the furnace model, providing a foundation for further analysis of temperature fields and emission characteristics.

[0085] Computational fluid dynamics (CFD) simulations were used to couple the combustion model generated in the first two steps with the gridded model. Numerical calculations were then performed to determine the three-dimensional furnace temperature field for different coal qualities. Analysis of the temperature field distribution determined the furnace temperature distribution characteristics for each coal quality, allowing for further comparison of the efficiency and emission characteristics of the denitrification and desulfurization systems. The results of this step provided the necessary temperature and reaction foundation for subsequent NOx and SO2 emission analysis.

[0086] Example 5:

[0087] The specific method of combining the detailed structure of the denitrification system with the furnace temperature field to obtain the denitrification efficiency and NOx emission index under the three-dimensional model is as follows:

[0088] Using the previously obtained three-dimensional furnace temperature field model, the temperature distribution at various locations within the furnace is determined. Based on this temperature field analysis, NOx generation models (such as thermal NOx, rapid NOx, or fuel-based NOx generation mechanisms) are applied. The combustion characteristics and NOx generation rates of different coal qualities are incorporated into the model to simulate the NOx generation process and concentration distribution within the furnace. This step allows the NOx generation sources and concentration distribution in various areas of the furnace to be determined, providing a basis for the reductant injection strategy.

[0089] After determining the NOx generation distribution, the injection process of the reducing agent (such as ammonia or urea) within the furnace is simulated, taking into account the injection system structure of the denitrification system. Parameters such as injection position, nozzle type, injection angle, and flow rate are input into the model, and computational fluid dynamics (CFD) is used to simulate the mixing and diffusion of the reducing agent in the high-temperature flue gas. Based on the reaction rate and reduction characteristics of the reducing agent at each temperature layer, the NOx reduction efficiency at each injection point is calculated. This step combines the reducing agent distribution with the NOx generation distribution to accurately predict the spatial efficiency of the denitrification process.

[0090] The obtained NOx reduction efficiency is used to calculate the overall denitration efficiency. The reduction effects at each injection point and temperature layer are summarized to calculate the overall NOx removal efficiency of the denitration system. The NOx emission index is then calculated based on the difference in NOx concentration before and after removal. Finally, the NOx emission index is compared with relevant emission standards to determine the denitration system's performance and compliance with emission standards under these operating conditions. This step integrates the temperature field, reducing agent distribution, and NOx generation and reduction characteristics, providing precise data support for optimizing denitration system design and operating parameters.

[0091] Example 6:

[0092] The specific method of combining the detailed structure of the desulfurization system with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model is as follows:

[0093] The three-dimensional furnace temperature field and flue gas flow model are used to determine the amount and concentration distribution of SO₂ in the flue gas. By analyzing the flue gas flow rate, temperature, and initial SO₂ concentration, the SO₂ concentration distribution at the flue gas absorber inlet is determined and corrected based on the sulfur content and combustion conditions of different coal qualities. This step provides initial SO₂ distribution data for the desulfurization reaction, facilitating subsequent simulations of the absorbent-SO₂ reaction.

[0094] After determining the initial SO2 concentration in the flue gas, the contact and reaction between SO2 and the absorbent (e.g., limestone slurry) is simulated based on the absorbent spray system structure within the absorber tower. Parameters such as the number of spray layers, nozzle distribution, spray flow rate, and absorbent concentration are imported into the model. Computational fluid dynamics (CFD) is used to simulate the absorbent's distribution, flow, and chemical reaction with SO2. The local desulfurization efficiency of each spray layer is calculated based on the reaction rate and contact time of the spray liquid with SO2. This step integrates the characteristics of flue gas flow and the spray system, providing the basis for the final calculation of the overall desulfurization efficiency.

[0095] Based on the local desulfurization efficiency of each spray layer, the overall desulfurization efficiency within the absorber is calculated, and the SO2 emission index is determined based on the SO2 concentration at the absorber outlet. By comparing the inlet and outlet SO2 concentrations, the overall SO2 removal efficiency of the absorber is calculated. The SO2 emission index is then compared with the emission standard to evaluate the effectiveness of the desulfurization system under these operating conditions. This step integrates the flue gas characteristics, SO2 generation, and local desulfurization efficiency from the previous two steps, providing data support for optimizing absorbent usage and spray system design.

[0096] Example 7:

[0097] Based on the denitrification efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion. The specific method for adjusting the maximum amount of sludge mixed combustion corresponding to the NOx emission is as follows:

[0098] Key combustion characteristics of sludge were studied, including its volatile matter, nitrogen content, moisture, ash content, and calorific value. Sludge has a high nitrogen content, which can increase NOx generation during combustion. Furthermore, the volatile matter and moisture content can affect the furnace temperature field. Based on these characteristics, a preliminary co-combustion model was established, using the relationship between the sludge co-combustion ratio and the furnace temperature field, flue gas flow characteristics, and initial NOx generation as input data. This provided the foundational data for subsequent NOx generation simulations.

[0099] Based on the preliminary co-combustion model, combined with the furnace temperature field and flue gas flow models, the NOx generation process under different sludge co-combustion ratios was simulated. The co-combustion ratio, sludge combustion characteristics, and initial NOx generation characteristics were introduced, and computational fluid dynamics (CFD) simulations were used to analyze the impact of increasing the co-combustion ratio on NOx generation. The focus was on analyzing the effect of different co-combustion ratios on combustion temperature and the changes in NOx generation rate. The NOx generation and concentration distribution were calculated for each co-combustion ratio, laying the foundation for the subsequent calculation of denitrification efficiency.

[0100] Based on the simulated NOx generation and the denitrification system's reaction efficiency, the final NOx emissions at various sludge blending ratios are calculated. By comparing NOx emissions at different blending ratios with environmental standards, the critical NOx emission value for sludge blending is determined—that is, the maximum blending ratio that meets emission requirements. A curve is also generated that correlates the blending ratio with NOx emissions, providing a basis for optimizing boiler system control. This step integrates the sludge blending characteristics, NOx generation characteristics, and denitrification system efficiency, enabling a comprehensive assessment of NOx emissions at different blending ratios.

[0101] Example 8:

[0102] Based on the desulfurization efficiency and SO2 emission index under the three-dimensional model, the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion. The specific method for adjusting the maximum amount of sludge mixed combustion corresponding to the SO2 emission is as follows:

[0103] The sulfur content and combustion characteristics of the sludge were analyzed to determine the sulfur release characteristics within the furnace at different blending ratios. The sulfur content in the sludge directly affects SO2 generation, while the moisture and ash content of the sludge also affect the furnace temperature field and flue gas composition. Based on this data, a preliminary blending model was developed, using the relationship between the sludge blending ratio, sulfur content, and SO2 generation as input parameters. This provided the basis for accurate simulation of SO2 generation in subsequent steps.

[0104] Based on the preliminary model, the SO2 generation process was simulated under different sludge co-combustion ratios, combining the furnace temperature field and flue gas flow characteristics. Parameters such as the sludge sulfur content and co-combustion ratio were imported into the computational fluid dynamics (CFD) model to analyze the impact of different co-combustion ratios on combustion temperature and SO2 generation rate. The CFD simulations determined the SO2 concentration distribution and generation rate at each co-combustion ratio, laying the foundation for the subsequent desulfurization efficiency calculations. This step provides accurate SO2 generation data for further analysis of the desulfurization system's adaptability and desulfurization efficiency.

[0105] Based on the simulated SO2 generation and concentration distributions, combined with the desulfurization system efficiency model, the final SO2 emissions were calculated for different sludge blending ratios. The SO2 removal performance at each blending ratio was evaluated based on the desulfurization system's absorption efficiency, and the SO2 concentration at the desulfurization system outlet was calculated. The SO2 emissions for each blending ratio were compared with environmental standards to determine the critical SO2 emission value for sludge blending—the maximum sludge blending amount that meets emission standards. A curve was generated that correlated the blending ratio with SO2 emissions, providing a basis for decision-making on optimizing boiler system operation.

[0106] Example 9:

[0107] The maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions are trained through BP neural network to obtain the specific method of the maximum blending amount of boiler sludge as follows:

[0108] The data of the maximum sludge blending amount corresponding to the NOx and SO2 emissions under the three-dimensional model are collected and sorted, and the data are normalized or standardized to adapt to the input requirements of the BP neural network. At the same time, the input features and output targets of the BP neural network are determined, wherein the input features include the threshold data of the NOx and SO2 emissions, and the output target is the maximum sludge blending amount of the boiler.

[0109] According to the pretreated data, a BP neural network model is constructed, and appropriate number of layers, nodes and activation functions are set. The data set related to the NOx and SO2 emissions is used for training the model, so that the model can gradually learn the nonlinear relationship between the NOx and SO2 emissions and the sludge blending amount. In the training process, the network weight is continuously adjusted through the back propagation algorithm, the prediction error is reduced, and the model performance is optimized.

[0110] An independent data set is used to verify the trained BP neural network model to ensure that the model has good generalization ability and prediction accuracy. Then, the actual operation data of the NOx and SO2 emissions are input into the model, and the maximum sludge blending amount of the boiler is predicted. The final model will be used to guide the sludge blending operation of the boiler in real time, optimize the blending amount, and meet the emission standards at the same time.

[0111] Embodiment 10:

[0112] Referring to Figure 3 The present application also provides an electronic device 100 for determining the sludge blending amount of a boiler based on a coupled BP neural network. The electronic device 100 comprises a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0113] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for determining the amount of boiler sludge co-combustion based on a coupled BP neural network as described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data (such as audio data) generated based on the use of the electronic device 100. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0114] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0115] The memory 101 in the electronic device 100 stores a plurality of instructions for implementing a method for determining the amount of boiler sludge blending based on a coupled BP neural network. The processor 102 can execute the plurality of instructions to implement:

[0116] Obtain the detailed structure of the denitrification system and desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitrification system and desulfurization system;

[0117] Based on the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, a relevant model of different coal qualities in the furnace is established. The CFD simulation values ​​are introduced into the relevant model to simulate the furnace temperature field.

[0118] The detailed structure of the denitrification system is combined with the furnace temperature field to obtain the denitrification efficiency and NOx emission index under the three-dimensional model;

[0119] The detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization efficiency and SO2 emission index under the three-dimensional model;

[0120] Based on the denitrification efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion, and the maximum amount of regulated sludge mixed combustion corresponding to the NOx emission is obtained.

[0121] Based on the desulfurization efficiency and SO2 emission index under the three-dimensional model, the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion, and the maximum amount of regulated sludge mixed combustion corresponding to the SO2 emission is obtained.

[0122] The maximum blending amount of regulating sludge corresponding to NOx emission and the maximum blending amount of regulating sludge corresponding to SO2 emission are trained through BP neural network to obtain the maximum blending amount of boiler sludge.

[0123] Example 11:

[0124] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0125] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for determining the amount of boiler sludge blending based on a coupled BP neural network, characterized in that: The following steps are involved: Obtain the detailed structure of the denitrification system and desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitrification system and desulfurization system. The specific method is as follows: The reactor structure, injection system, catalyst layout, and flue gas parameters in the denitrification system are obtained as parameter information, and the absorption tower structure, spray system, filler characteristics, and flue gas flow parameters in the desulfurization system are obtained as boundary information; A three-dimensional geometric model is established based on the acquired parameter information, and meshing is performed. The boundary information is input into the three-dimensional geometric model to obtain a furnace mesh model. Based on the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, a relevant model of different coal qualities in the furnace is established. The CFD simulation values ​​are introduced into the relevant model to simulate the furnace temperature field. The detailed structure of the denitrification system is combined with the furnace temperature field to obtain the denitrification efficiency and NOx emission index under the three-dimensional model; The detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization efficiency and SO2 emission index under the three-dimensional model; Based on the denitrification efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion, and the maximum amount of regulated sludge mixed combustion corresponding to the NOx emission is obtained. Based on the desulfurization efficiency and SO2 emission index under the three-dimensional model, the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion, and the maximum amount of regulated sludge mixed combustion corresponding to the SO2 emission is obtained. The maximum blending amount of regulating sludge corresponding to NOx emission and the maximum blending amount of regulating sludge corresponding to SO2 emission are trained through BP neural network to obtain the maximum blending amount of boiler sludge.

2. The method for determining the amount of boiler sludge blending based on coupled BP neural network according to claim 1 is characterized in that: Based on the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, a relevant model of different coal qualities in the furnace is established. The CFD simulation values ​​are introduced into the relevant model to simulate the furnace temperature field. The specific method is as follows: Obtain the combustion characteristic parameters of different coal qualities, and establish a preliminary combustion model based on the combustion characteristic parameters of different coal qualities using thermodynamics and combustion models; Import the combustion characteristic parameters of different coal qualities into the furnace grid model to simulate the combustion process of different coal qualities in the furnace; After coupling the preliminary combustion model and the furnace mesh model, CFD simulation was used to obtain the furnace temperature field.

3. The method for determining the amount of boiler sludge blending based on coupled BP neural network according to claim 1 is characterized in that: The specific method of combining the detailed structure of the denitrification system with the furnace temperature field to obtain the denitrification efficiency and NOx emission index under the three-dimensional model is as follows: Based on the furnace temperature field, the temperature distribution at different locations in the furnace is determined. Combined with the combustion characteristics and NOx generation rates of different coal qualities, the NOx generation process and concentration distribution in the furnace are simulated. Based on the NOx generation process and concentration distribution in the furnace and the detailed structure of the denitrification system, the injection process of the reducing agent in the furnace is simulated. CFD is used to simulate the mixing and diffusion of the reducing agent in the flue gas. Based on the reaction rate and reduction characteristics of the reducing agent at each temperature layer, the NOx reduction efficiency at each injection point is calculated. According to the NOx reduction efficiency of each injection point, the denitrification efficiency of each injection point is obtained. The denitrification efficiency of each injection point is summarized to obtain the denitrification removal efficiency and NOx emission index under the three-dimensional model.

4. The method for determining the amount of boiler sludge blending based on coupled BP neural network according to claim 1 is characterized in that: The specific method of combining the detailed structure of the desulfurization system with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model is as follows: According to the furnace temperature field, determine the generation amount and concentration distribution of SO2 in the flue gas, analyze the generation amount and concentration distribution in the flue gas, and obtain the SO2 distribution data in the flue gas; Based on the SO2 distribution data in the flue gas and the detailed structure of the desulfurization system, the contact and reaction process between SO2 and the absorbent is simulated through CFD to obtain the local desulfurization efficiency of each spray layer; According to the local desulfurization efficiency of each spray layer, the desulfurization removal efficiency and SO2 emission index are summarized.

5. The method for determining the amount of boiler sludge blended combustion based on coupled BP neural network according to claim 1 is characterized in that: Based on the denitrification efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission when increasing the amount of sludge mixed combustion. The specific method for adjusting the maximum amount of sludge mixed combustion corresponding to the NOx emission is as follows: Obtain the combustion characteristics of sludge and establish a preliminary co-combustion model based on the combustion characteristics of sludge; Based on the preliminary co-combustion model, combined with the furnace temperature field and flue gas flow model, the NOx generation process under different sludge co-combustion ratios was simulated, and the NOx generation amount and concentration distribution under each co-combustion ratio were obtained; According to the NOx generation and concentration distribution under various sludge co-combustion ratios and the reaction efficiency of the denitrification system, the final NOx emissions under various sludge co-combustion ratios were obtained.

6. The method for determining the amount of boiler sludge blending based on coupled BP neural network according to claim 1 is characterized in that: Based on the desulfurization efficiency and SO2 emission index under the three-dimensional model, the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission when increasing the amount of sludge mixed combustion. The specific method for adjusting the maximum amount of sludge mixed combustion corresponding to the SO2 emission is as follows: Obtain the sulfur content and combustion characteristics of the sludge, obtain the release characteristics of sulfur in the furnace under different blending ratios, and establish a preliminary blending model; Based on the preliminary co-combustion model, combined with the furnace temperature field and flue gas flow characteristics, a CFD model was used to simulate the SO2 generation process under different sludge co-combustion ratios, and the effects of different co-combustion amounts on combustion temperature and SO2 generation rate were obtained. According to the influence of different sludge blending ratios on combustion temperature and SO2 generation rate, combined with the efficiency model of the desulfurization system, the final SO2 emissions under different sludge blending ratios are calculated.

7. The method for determining the amount of boiler sludge blended combustion based on coupled BP neural network according to claim 1, characterized in that: The maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions are trained through BP neural network to obtain the specific method of the maximum blending amount of boiler sludge as follows: Obtain the maximum amount of regulated sludge blended combustion corresponding to NOx emissions and the maximum amount of regulated sludge blended combustion corresponding to SO2 emissions, and perform normalization and standardization processing; A BP neural network model is constructed and trained using the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions to obtain the final BP neural network model; The maximum blending amount of regulated sludge corresponding to the actual NOx emissions and the maximum blending amount of regulated sludge corresponding to the SO2 emissions are input into the final BP neural network model to obtain the maximum blending amount of boiler sludge.

8. The system for determining the amount of boiler sludge blended combustion based on coupled BP neural network is characterized by: include: The furnace grid model building module is used to obtain the detailed structure of the denitrification system and desulfurization system in the boiler, and build the furnace grid model based on the detailed structure of the denitrification system and desulfurization system. The specific method is as follows: The reactor structure, injection system, catalyst layout, and flue gas parameters in the denitrification system are obtained as parameter information, and the absorption tower structure, spray system, filler characteristics, and flue gas flow parameters in the desulfurization system are obtained as boundary information; A three-dimensional geometric model is established based on the acquired parameter information, and meshing is performed. The boundary information is input into the three-dimensional geometric model to obtain a furnace mesh model. The furnace temperature field acquisition module is used to establish relevant models of different coal qualities in the furnace based on the furnace grid model and combined with the real-time data of the denitrification system and desulfurization system. The CFD simulation values ​​are then introduced into the relevant models to simulate the furnace temperature field. The denitrification efficiency acquisition module is used to combine the detailed structure of the denitrification system with the furnace temperature field to obtain the denitrification removal efficiency and NOx emission index under the three-dimensional model; The desulfurization efficiency acquisition module is used to combine the detailed structure of the desulfurization system with the furnace temperature field to obtain the desulfurization efficiency and SO2 emission index under the three-dimensional model; The NOx blending amount module is used to obtain the criterion for the minimum NOx emission amount of boiler denitrification and the critical criterion for NOx emission amount by increasing the sludge blending amount based on the denitrification efficiency and NOx emission index under the three-dimensional model. The module compares the different temperatures of the boiler furnace with the criterion for the minimum NOx emission amount of boiler denitrification and the critical criterion for NOx emission amount by increasing the sludge blending amount to obtain the maximum regulated sludge blending amount corresponding to the NOx emission amount. The SO2 blending amount module is used to obtain the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission by increasing the amount of sludge blending based on the desulfurization removal efficiency and SO2 emission index under the three-dimensional model. The module compares the different temperatures of the boiler furnace with the criterion for the minimum SO2 emission of boiler desulfurization and the critical criterion for SO2 emission by increasing the amount of sludge blending to obtain the maximum amount of regulated sludge blending corresponding to the SO2 emission. The model processing module is used to train the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions through BP neural network to obtain the maximum blending amount of boiler sludge.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for determining the amount of boiler sludge blended combustion based on a coupled BP neural network according to any one of claims 1 to 7 are implemented.

Images