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

Abstract

The invention belongs to the field of boiler sludge blending combustion amount calculation, and discloses a method and a system for determining the boiler sludge blending combustion amount based on a coupled BP neural network, which can effectively reduce the high-temperature corrosion phenomenon caused by tangential flame wall painting by accurately adjusting the sludge blending combustion amount and avoiding the too high local temperature. The BP neural network model can predict temperature field distribution under different blending combustion amounts, the temperature field distribution is controlled within a safe temperature range, and the service life of the boiler is prolonged. According to the method, the sludge blending combustion amount is optimized based on the real-time model of the denitration and desulfurization system, so that the discharge amount of NOx and SO2 is controlled below a critical value. By predicting and controlling the discharge amount, the environmental protection standard is met while the sludge is combusted in a blending manner, and the discharge of pollutants is reduced.

Description

Technical Field

[0001] The invention belongs to the field of boiler sludge blending and combustion amount calculation, and in particular relates to a method and a system for determining boiler sludge blending and combustion amount based on a coupled BP neural network. Background Art

[0002] However, among the current methods for treating sludge, the boiler co-firing method can fully utilize the organic components in the sludge, with a fast and thorough treatment speed. In addition, the coal-fired boiler co-firing treatment has the dual advantages of low transformation investment and saving coal usage, making it a very advantageous treatment method.

[0003] However, the mixing and burning of coal-fired boilers will lead to reduced boiler efficiency, increased NOx treatment capacity of the denitrification system, increased SO2 treatment capacity of the desulfurization system, increased dust removal system treatment capacity, and the presence of dioxins and other toxic gases in the treated flue gas. These problems restrict the mixing and burning of sludge in coal-fired boilers. In the past, the maximum mixing and burning of sludge was obtained based on experience such as unit size and auxiliary system processing capacity, which was somewhat blind, making the actual maximum mixing and burning of sludge often much lower than the capacity that coal-fired boilers can bear.

[0004] Patent document CN113790456B provides a method and system for calculating the maximum sludge blending amount of a coal-fired boiler, which is based on the relevant parameters and sludge characteristics of the coal-fired boiler, coal mill, denitrification system, desulfurization system, dust removal system, and wastewater system under typical loads, and on the premise of ensuring the safe operation of the coal-fired boiler, in order to maximize the amount of sludge that can be blended under typical loads, and can correct the maximum sludge blending amount in real time according to the target power generation and actual power generation of the coal-fired unit. There are still the following disadvantages: 1. This calculation method can only calculate the maximum sludge blending amount under typical loads and design conditions and coal quality, which is difficult to adapt to the current situation of a stronger degree of coal mixing in power plants, and may lead to an overestimation of the maximum sludge blending amount under worse coal quality conditions.

[0005] Patent document CN115951012A provides a method for determining the maximum blending rate of coal-fired coupled sludge. Based on theoretical calculations, the method and system for gradually determining the maximum blending rate of sludge are determined by blending test, 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 the limiting conditions. However, there are still the following disadvantages: 1. Field measurements need to be carried out by blending test and multiple measurements of multiple working conditions are required, which can only represent the coal quality and working conditions at that time, and the maximum blending rate is not accurately estimated. Summary of the invention

[0006] The purpose of the present invention is to overcome the problem that the large tangential circle flame of a wall-type tangential circle boiler is easy to brush the wall and cause high-temperature corrosion in the furnace, and to provide a method and system for determining the amount of boiler sludge blending based on a coupled BP neural network.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: 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: Obtain the detailed structure of the denitration system and desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitration system and desulfurization system; According to the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, the relevant models of different coal qualities in the furnace are established, and the CFD simulation values ​​are brought into the relevant models to simulate the furnace temperature field; 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; The detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model; 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 by increasing the amount of sludge blended 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 by increasing the amount of sludge blended combustion, and the maximum amount of regulated sludge blended combustion corresponding to the NOx emission is obtained. According to 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 of 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 of increasing the sludge blending amount, and the maximum sludge blending amount 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.

[0008] A further improvement of the present invention is that the detailed structure of the denitration system and the desulfurization system in the boiler is obtained, and the specific method of establishing the furnace grid model according to the detailed structure of the denitration system and the desulfurization system 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 according to 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.

[0009] A further improvement of the present invention is 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, and the CFD simulation value is brought into the relevant model. The specific method of simulating the furnace temperature field 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.

[0010] A further improvement of the present invention is that the detailed structure of the denitration system is combined with the furnace temperature field, and the specific method for obtaining the denitration removal efficiency and NOx emission index under the three-dimensional model is as follows: According to the furnace temperature field, the temperature distribution at different positions in the furnace is determined. Combining the combustion characteristics of different coal qualities and the NOx generation rate, the generation process and concentration distribution of NOx in the furnace are simulated. According to the generation process and concentration distribution of NOx in the furnace, combined with the detailed structure of the denitrification system, the injection process of the reducing agent in the furnace is simulated, and CFD is used to simulate the mixing and diffusion of the reducing agent in the flue gas. According to the reaction rate and reduction characteristics of the reducing agent at each temperature layer, the NOx reduction efficiency of 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.

[0011] A further improvement of the present invention is that the detailed structure of the desulfurization system is combined with the furnace temperature field, and the specific method for obtaining 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 by 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.

[0012] The present invention is further improved in that, according to the denitration efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitration and the critical criterion for NOx emission of increasing the sludge blending amount are obtained, and the different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitration and the critical criterion for NOx emission of increasing the sludge blending amount, and the specific method for adjusting the maximum sludge blending amount corresponding to the NOx emission is obtained as follows: Obtain the combustion characteristics of sludge and establish a preliminary blending model based on the combustion characteristics of sludge; Based on the preliminary blending model, combined with the furnace temperature field and flue gas flow model, the NOx generation process under different sludge blending ratios was simulated to obtain the NOx generation amount and concentration distribution under each blending ratio. According to the NOx generation and concentration distribution under various sludge blending ratios and the reaction efficiency of the denitrification system, the final NOx emissions under various sludge blending ratios were obtained.

[0013] The present invention is further improved in that, according to the desulfurization removal efficiency and SO2 emission index under the three-dimensional model, the criterion of the minimum SO2 emission of boiler desulfurization and the critical criterion of SO2 emission of increasing the sludge blending amount are obtained, and the different temperatures of the boiler furnace are compared with the criterion of the minimum SO2 emission of boiler desulfurization and the critical criterion of SO2 emission of increasing the sludge blending amount, and the specific method of obtaining the maximum sludge blending amount 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 blending model, combined with the furnace temperature field and flue gas flow characteristics, the CFD model was used to simulate the SO2 generation process under different sludge blending ratios, and the effects of different blending amounts on the combustion temperature and SO2 generation rate were obtained. According to the influence of different blending amounts 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.

[0014] A further improvement of the present invention is that 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 are trained through a BP neural network, and the specific method for obtaining the maximum blending amount of the boiler sludge is 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 the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions are used to train the BP neural network model to obtain the final BP neural network model; 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.

[0015] 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: A furnace grid model building module is used to obtain the detailed structure of the denitration system and the desulfurization system in the boiler, and to build a furnace grid model based on the detailed structure of the denitration system and the desulfurization system; 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 the desulfurization system, and bring the CFD simulation values ​​into the relevant model to simulate the furnace temperature field; The denitration efficiency acquisition module is used to combine the detailed structure of the denitration system with the furnace temperature field to obtain the denitration 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 removal 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 of boiler denitrification and the critical criterion for NOx emission of increasing sludge blending amount according to the denitrification removal efficiency and NOx emission index under the three-dimensional model, and compare the different temperatures of the boiler furnace with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission of increasing sludge blending amount to obtain the maximum regulated sludge blending amount corresponding to the NOx emission; 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 of increasing sludge blending amount according to the desulfurization removal efficiency and SO2 emission index under the three-dimensional model, and compare 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 of increasing sludge blending amount to obtain the maximum sludge blending amount corresponding to the SO2 emission; The model processing module is used to train the maximum blending amount of the regulating sludge corresponding to the NOx emission and the maximum blending amount of the regulating sludge corresponding to the SO2 emission through the BP neural network to obtain the maximum blending amount of the boiler sludge.

[0016] In a third aspect, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for determining the amount of boiler sludge blending based on a coupled BP neural network are implemented.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention can effectively reduce the high temperature corrosion caused by the wall brushing of the circular flame by accurately adjusting the amount of sludge blending. The BP neural network model can predict the temperature field distribution under different blending amounts, control it within a safe temperature range, and extend the service life of the boiler. The present invention optimizes the amount of sludge blending based on the real-time model of the denitrification and desulfurization system, so that the NOx and SO2 emissions are controlled below the critical value. By predicting and controlling the emission amount, it is achieved that the environmental protection standards are met while blending the sludge, and the emission of pollutants is reduced. Under the premise of ensuring safety and environmental protection, the present invention can increase the maximum amount of sludge blending, thereby realizing more sludge resource recycling and reducing fuel costs. This method of optimizing the blending amount not only improves the combustion efficiency, but also promotes the recycling of solid waste, which helps to promote sustainable development. The present invention couples the denitrification and desulfurization system with the furnace temperature field, and the optimized sludge blending amount helps to form a more stable combustion temperature field and improve the 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 tangentially fired boilers, but also reduce pollutant emissions, increase the amount of sludge blended combustion and combustion efficiency, thereby achieving economic and environmentally friendly boiler operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of the present invention; Figure 2 is a system diagram of the present invention; Figure 3 This is a system diagram of Example 10. DETAILED DESCRIPTION

[0019] 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.

[0020] Embodiment 1: See also Figure 1 The method for determining the amount of boiler sludge blending based on coupled BP neural network includes the following steps: S1, obtaining the detailed structures of the denitrification system and the desulfurization system in the boiler, and establishing a furnace grid model according to the detailed structures of the denitrification system and the desulfurization system.

[0021] S2, based on the furnace grid model, combined with the real-time data of the denitrification system and the 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.

[0022] 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.

[0023] S4, the detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model.

[0024] 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 by increasing the amount of sludge blended 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 by increasing the amount of sludge blended combustion, and the maximum amount of regulated sludge blended combustion corresponding to the NOx emission is obtained.

[0025] S6. According to 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 by 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 by increasing the sludge blending amount, and the maximum sludge blending amount corresponding to the SO2 emission is obtained.

[0026] S7, training the maximum blending amount of the regulating sludge corresponding to the NOx emission and the maximum blending amount of the regulating sludge corresponding to the SO2 emission through a BP neural network to obtain the maximum blending amount of the boiler sludge.

[0027] Embodiment 2: See also Figure 2 , the system for determining the amount of boiler sludge blending based on coupled BP neural network includes: A furnace grid model building module is used to obtain the detailed structure of the denitration system and the desulfurization system in the boiler, and to build a furnace grid model based on the detailed structure of the denitration system and the desulfurization system; 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 the desulfurization system, and bring the CFD simulation values ​​into the relevant model to simulate the furnace temperature field; The denitration efficiency acquisition module is used to combine the detailed structure of the denitration system with the furnace temperature field to obtain the denitration 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 removal 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 of boiler denitrification and the critical criterion for NOx emission of increasing sludge blending amount according to the denitrification removal efficiency and NOx emission index under the three-dimensional model, and compare the different temperatures of the boiler furnace with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission of increasing sludge blending amount to obtain the maximum regulated sludge blending amount corresponding to the NOx emission; 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 of increasing sludge blending amount according to the desulfurization removal efficiency and SO2 emission index under the three-dimensional model, and compare 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 of increasing sludge blending amount to obtain the maximum sludge blending amount corresponding to the SO2 emission; The model processing module is used to train the maximum blending amount of the regulating sludge corresponding to the NOx emission and the maximum blending amount of the regulating sludge corresponding to the SO2 emission through the BP neural network to obtain the maximum blending amount of the boiler sludge.

[0028] Embodiment 3: The specific method of obtaining the detailed structure of the denitrification system and the desulfurization system in the boiler and establishing the furnace grid model according to the detailed structure of the denitrification system and the desulfurization system is as follows: Comprehensively obtain detailed structural information of the denitrification and desulfurization systems, including the physical and chemical parameters of key components such as reactors, injection systems, catalysts, absorption towers, and spray systems. These data provide an accurate basis for subsequent model construction.

[0029] The collected detailed information is input into the 3D modeling tool to build a detailed geometric model and perform meshing. The boundary conditions such as flue gas flow rate and temperature are accurately set in the model so that the model can truly simulate the operating environment of the denitrification and desulfurization system.

[0030] After the model is initially established, the accuracy of the model is verified by comparing it with the actual operating data of the system or the CFD simulation results. According to the comparison results, 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 basis for subsequent analysis.

[0031] Embodiment 4: According to the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, the relevant models of different coal qualities in the furnace are established, and the CFD simulation values ​​are brought into the relevant models. The specific method of simulating the furnace temperature field is as follows: Collect and analyze the key combustion characteristic parameters of different coal qualities, including volatile matter content, ash content, fixed carbon content, calorific value, ignition temperature, etc. These parameters can directly affect the intensity and speed of the combustion reaction, and ultimately affect the distribution of the temperature field in the furnace. Based on these data, a preliminary combustion model is established using thermodynamics and combustion models to ensure that the model can reflect the combustion behavior of different types of coal, laying the foundation for subsequent furnace temperature field modeling.

[0032] Based on the preliminary combustion model, the combustion characteristic parameters of different coal qualities are imported into the furnace grid model. The furnace interior is divided into fine grids, and boundary conditions such as coal quality, air flow and temperature are set based on different grid positions, so that the model can accurately simulate the combustion process of different coal qualities in the furnace. Through this step, the combustion thermodynamic characteristics of different coal types can be reflected in the furnace model, providing a basis for further analysis of temperature field and emission characteristics.

[0033] Computational fluid dynamics (CFD) simulation is used to couple the combustion model and grid model generated in the first two steps, and the three-dimensional temperature field of the furnace under different coal qualities is obtained through numerical calculation. By analyzing the distribution of the temperature field, the temperature distribution characteristics of each coal quality in the furnace are determined, and the efficiency and emission characteristics of the denitrification and desulfurization systems are further compared. The results of this step can provide the necessary temperature and reaction basis for the subsequent NOx and SO2 emission analysis.

[0034] Embodiment 5: The specific method of combining 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 is as follows: The temperature distribution at different positions in the furnace is determined by using the three-dimensional furnace temperature field model obtained in the early stage. Based on the temperature field analysis, the NOx generation model (such as thermal NOx, rapid NOx or fuel NOx generation mechanism) is applied, and the combustion characteristics and NOx generation rate of different coal qualities are introduced into the model to simulate the generation process and concentration distribution of NOx in the furnace. Through this step, the NOx generation source and concentration distribution in each area of ​​the furnace can be obtained, providing a basis for the injection strategy of the reducing agent.

[0035] After obtaining the NOx generation distribution, the injection process of the reducing agent (such as ammonia or urea) in the furnace is simulated in combination with the injection system structure of the denitrification system. The injection position, nozzle type, injection angle, flow rate and other parameters 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. According to the reaction rate and reduction characteristics of the reducing agent at each temperature layer, the NOx reduction efficiency of each injection point is calculated. This step combines the reducing agent distribution with the NOx generation distribution, and can accurately predict the spatial efficiency of the denitrification process.

[0036] The overall denitrification efficiency is calculated by the obtained NOx reduction efficiency. The reduction effects of each injection point and different temperature layers are summarized to calculate the overall removal efficiency of the denitrification system for NOx, and the NOx emission index is obtained based on the difference in NOx concentration before and after removal. Finally, the NOx emission index is compared with the relevant emission standards to determine the performance of the denitrification system and the compliance of emissions under this condition. This step integrates the temperature field, reductant distribution, and NOx generation and reduction characteristics, providing accurate data support for optimizing the design and operation parameters of the denitrification system.

[0037] Embodiment 6: 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: The three-dimensional temperature field of the furnace and the flue gas flow model are used to determine the generation 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 of the flue gas at the entrance of the absorption tower can be obtained, and it can be corrected in combination with the sulfur content and combustion conditions of different coal qualities. This step provides the initial SO2 distribution data for the desulfurization reaction, which is helpful for simulating the reaction between the absorbent and SO2 in the subsequent steps.

[0038] After obtaining the initial concentration of SO2 in the flue gas, the contact and reaction process between SO2 and the absorbent (such as limestone slurry) is simulated according to the structure of the spray system of the absorbent in the absorber. The parameters such as the number of spray layers, nozzle distribution, spray flow rate and absorption liquid concentration are imported into the model, and the distribution, flow and chemical reaction of the absorbent with SO2 are simulated by computational fluid dynamics (CFD). According to the reaction rate and contact time of the spray liquid with SO2, the local desulfurization efficiency of each spray layer is calculated. This step combines the characteristics of flue gas flow and spray system, providing a basis for the final calculation of the overall desulfurization efficiency.

[0039] According to the local desulfurization efficiency of each spray layer, the overall desulfurization efficiency in the absorber is calculated, and the SO2 emission index is determined according to the SO2 concentration at the outlet of the absorber. By comparing the inlet and outlet SO2 concentrations, the overall removal effect of the absorber on SO2 is calculated, and the SO2 emission index is compared with the emission standard to evaluate the effect of the desulfurization system under this working condition. This step integrates the flue gas characteristics, SO2 generation and local desulfurization efficiency in the first two steps, and provides data support for optimizing the use of absorbents and spray system design.

[0040] Embodiment 7: According to the denitration efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitration and the critical criterion for NOx emission by increasing the amount of sludge blending are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitration and the critical criterion for NOx emission by increasing the amount of sludge blending. The specific method for obtaining the maximum amount of sludge blending corresponding to the NOx emission is as follows: The key combustion characteristics of sludge are studied, including its volatile matter, nitrogen content, moisture, ash content and combustion calorific value. The nitrogen content of sludge is high, which may lead to an increase in NOx generation during combustion. At the same time, the volatile matter and moisture content may affect the furnace temperature field. Based on these characteristics, a preliminary blending model is established, and the relationship between the sludge blending ratio and the furnace temperature field, flue gas flow characteristics and initial NOx generation is used as input data to provide basic data for the NOx generation simulation in subsequent steps.

[0041] On the basis of the preliminary blending model, combined with the furnace temperature field and flue gas flow model, the NOx generation process under different sludge blending ratios is simulated. The blending ratio, sludge combustion characteristics and initial NOx generation characteristics are introduced, and the effect of increasing the blending ratio on NOx generation is analyzed through computational fluid dynamics (CFD) simulation. The focus is on analyzing the effect of different blending amounts on the combustion temperature and the change in NOx generation rate, calculating the NOx generation and concentration distribution under each blending ratio, and laying the foundation for the calculation of denitrification efficiency in the next step.

[0042] Based on the simulated NOx generation, combined with the reaction efficiency of the denitrification system, the final NOx emissions at each sludge blending ratio are calculated. By comparing the NOx emissions at different blending ratios with environmental protection standards, the critical value of NOx emissions for sludge blending is determined, that is, the maximum blending ratio that meets the emission requirements. At the same time, a relationship curve between the blending ratio and NOx emissions is generated to provide a basis for the optimal control of the boiler system. This step integrates the sludge blending characteristics, NOx generation characteristics and denitrification system efficiency, and realizes a comprehensive evaluation of NOx emissions at different blending ratios.

[0043] Embodiment 8: According to 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 of 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 of increasing the sludge blending amount. The specific method for adjusting the maximum sludge blending amount corresponding to the SO2 emission is as follows: Analyze the sulfur content in the sludge and its combustion characteristics, and determine the release characteristics of sulfur in the furnace under different blending ratios. The sulfur content in the sludge will directly affect the amount of SO2 generated, and the moisture and ash content of the sludge will also affect the furnace temperature field and flue gas composition. Based on these data, a preliminary blending model is established, and the relationship between the sludge blending ratio, sulfur content and SO2 generation is used as input parameters to provide a basis for the accurate simulation of SO2 generation in subsequent steps.

[0044] On the basis of the preliminary model, combined with the furnace temperature field and flue gas flow characteristics, the SO2 generation process under different sludge blending ratios is simulated. The parameters such as the sulfur content and blending ratio of the sludge are imported into the computational fluid dynamics (CFD) model to analyze the effects of different blending amounts on the combustion temperature and SO2 generation rate. Through CFD simulation, the SO2 concentration distribution and generation rate under each blending ratio are obtained, laying the foundation for the next step of desulfurization efficiency calculation. This step can provide accurate SO2 generation data and further analyze the adaptability and desulfurization efficiency of the desulfurization system.

[0045] Based on the simulated SO2 generation and concentration distribution, combined with the efficiency model of the desulfurization system, the final SO2 emissions under different sludge blending ratios are calculated. According to the absorption efficiency of the desulfurization system, the SO2 removal effect under each blending ratio is evaluated, and the SO2 concentration at the outlet of the desulfurization system is calculated. The SO2 emissions at each blending ratio are compared with the environmental protection standards to determine the critical value of SO2 emissions for sludge blending, that is, the maximum sludge blending amount under the condition of meeting the emission standards. The relationship curve between the blending ratio and the SO2 emissions is generated to provide a decision-making basis for the optimized operation of the boiler system.

[0046] Embodiment 9: The maximum blending amount of the regulating sludge corresponding to the NOx emission and the maximum blending amount of the regulating sludge corresponding to the SO2 emission are trained through the BP neural network to obtain the specific method of the maximum blending amount of the boiler sludge as follows: Collect and organize the data of the maximum amount of sludge blending corresponding to the NOx and SO2 emissions under the three-dimensional model, and normalize or standardize these data to meet the input requirements of the BP neural network. At the same time, determine the input characteristics and output targets of the BP neural network, where the input characteristics include the threshold data of NOx and SO2 emissions, and the output target is the maximum amount of sludge blending for the boiler.

[0047] According to the preprocessed data, the BP neural network model is constructed, and the appropriate number of layers, nodes and activation functions are set. The model is trained using data sets related to NOx and SO2 emissions, so that the model can gradually learn the nonlinear relationship between NOx and SO2 emissions and the amount of sludge blending. During the training process, the network weights are continuously adjusted through the back propagation algorithm to reduce the prediction error and optimize the model performance.

[0048] The trained BP neural network model is verified using an independent data set to ensure that the model has good generalization ability and prediction accuracy. Then, the actual operation data of NOx and SO2 emissions are input into the model to predict the maximum amount of sludge blending in the boiler. The final model will be used to guide the sludge blending operation of the boiler in real time, optimizing the blending amount while meeting emission standards.

[0049] Embodiment 10: See also Figure 3 As shown, the present invention also provides an electronic device 100 for determining the amount of boiler sludge blending based on a coupled BP neural network; the electronic device 100 includes 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.

[0050] 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 blending based on the coupled BP neural network 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, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. 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 memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0051] 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 uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0052] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for determining the amount of boiler sludge blending based on a coupled BP neural network, and the processor 102 can execute the plurality of instructions to implement: Obtain the detailed structure of the denitration system and desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitration system and desulfurization system; According to the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, the relevant models of different coal qualities in the furnace are established, and the CFD simulation values ​​are brought into the relevant models to simulate the furnace temperature field; 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; The detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model; 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 by increasing the amount of sludge blended 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 by increasing the amount of sludge blended combustion, and the maximum amount of regulated sludge blended combustion corresponding to the NOx emission is obtained. According to 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 of 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 of increasing the sludge blending amount, and the maximum sludge blending amount 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.

[0053] Embodiment 11: 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. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0054] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] 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 flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 flowchart and / or block diagram. 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.

[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant 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 within 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 denitration system and desulfurization system in the boiler, and establish a furnace grid model based on the detailed structure of the denitration system and desulfurization system; According to the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, the relevant models of different coal qualities in the furnace are established, and the CFD simulation values ​​are brought into the relevant models to simulate the furnace temperature field; 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; The detailed structure of the desulfurization system is combined with the furnace temperature field to obtain the desulfurization removal efficiency and SO2 emission index under the three-dimensional model; 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 by increasing the amount of sludge blended 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 by increasing the amount of sludge blended combustion, and the maximum amount of regulated sludge blended combustion corresponding to the NOx emission is obtained. According to 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 of 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 of increasing the sludge blending amount, and the maximum sludge blending amount 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: The specific method of obtaining the detailed structure of the denitrification system and the desulfurization system in the boiler and establishing the furnace grid model according to the detailed structure of the denitrification system and the desulfurization system 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 according to 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.

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: According to the furnace grid model, combined with the real-time data of the denitrification system and the desulfurization system, the relevant models of different coal qualities in the furnace are established, and the CFD simulation values ​​are brought into the relevant models. The specific method of simulating the furnace temperature field 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.

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 denitrification system with the furnace temperature field to obtain the denitrification removal efficiency and NOx emission index under the three-dimensional model is as follows: According to the furnace temperature field, the temperature distribution at different positions in the furnace is determined. Combining the combustion characteristics of different coal qualities and the NOx generation rate, the generation process and concentration distribution of NOx in the furnace are simulated. According to the generation process and concentration distribution of NOx in the furnace, combined with the detailed structure of the denitrification system, the injection process of the reducing agent in the furnace is simulated, and CFD is used to simulate the mixing and diffusion of the reducing agent in the flue gas. According to the reaction rate and reduction characteristics of the reducing agent at each temperature layer, the NOx reduction efficiency of 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.

5. 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 by 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.

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: According to the denitration efficiency and NOx emission index under the three-dimensional model, the criterion for the minimum NOx emission of boiler denitration and the critical criterion for NOx emission by increasing the amount of sludge blending are obtained. The different temperatures of the boiler furnace are compared with the criterion for the minimum NOx emission of boiler denitration and the critical criterion for NOx emission by increasing the amount of sludge blending. The specific method for obtaining the maximum amount of sludge blending corresponding to the NOx emission is as follows: Obtain the combustion characteristics of sludge and establish a preliminary blending model based on the combustion characteristics of sludge; Based on the preliminary blending model, combined with the furnace temperature field and flue gas flow model, the NOx generation process under different sludge blending ratios was simulated to obtain the NOx generation amount and concentration distribution under each blending ratio. According to the NOx generation and concentration distribution under various sludge blending ratios and the reaction efficiency of the denitrification system, the final NOx emissions under various sludge blending ratios were obtained.

7. The method for determining the amount of boiler sludge blending based on coupled BP neural network according to claim 1 is characterized in that: According to 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 of 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 of increasing the sludge blending amount. The specific method for adjusting the maximum sludge blending amount 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 blending model, combined with the furnace temperature field and flue gas flow characteristics, the CFD model was used to simulate the SO2 generation process under different sludge blending ratios, and the effects of different blending amounts on the combustion temperature and SO2 generation rate were obtained. According to the influence of different blending amounts 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.

8. 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 maximum blending amount of the regulating sludge corresponding to the NOx emission and the maximum blending amount of the regulating sludge corresponding to the SO2 emission are trained through the BP neural network to obtain the specific method of the maximum blending amount of the 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 the maximum blending amount of regulated sludge corresponding to NOx emissions and the maximum blending amount of regulated sludge corresponding to SO2 emissions are used to train the BP neural network model to obtain the final BP neural network model; 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.

9. The system for determining the amount of boiler sludge blending based on coupled BP neural network is characterized by: include: A furnace grid model building module is used to obtain the detailed structure of the denitration system and the desulfurization system in the boiler, and to build a furnace grid model based on the detailed structure of the denitration system and the desulfurization system; 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 the desulfurization system, and bring the CFD simulation values ​​into the relevant model to simulate the furnace temperature field; The denitration efficiency acquisition module is used to combine the detailed structure of the denitration system with the furnace temperature field to obtain the denitration 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 removal 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 of boiler denitrification and the critical criterion for NOx emission of increasing sludge blending amount according to the denitrification removal efficiency and NOx emission index under the three-dimensional model, and compare the different temperatures of the boiler furnace with the criterion for the minimum NOx emission of boiler denitrification and the critical criterion for NOx emission of increasing sludge blending amount to obtain the maximum regulated sludge blending amount corresponding to the NOx emission; 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 of increasing sludge blending amount according to the desulfurization removal efficiency and SO2 emission index under the three-dimensional model, and compare 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 of increasing sludge blending amount to obtain the maximum sludge blending amount corresponding to the SO2 emission; The model processing module is used to train the maximum blending amount of the regulating sludge corresponding to the NOx emission and the maximum blending amount of the regulating sludge corresponding to the SO2 emission through the BP neural network to obtain the maximum blending amount of the boiler sludge.

10. 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 blending based on a coupled BP neural network according to any one of claims 1 to 8 are implemented.

Images