Non-design coal boiler combustion optimization method and system based on multi-field coupling simulation

Abstract

This invention specifically provides a method and system for optimizing boiler combustion of non-designed coal types based on multi-field coupled simulation. The method includes: acquiring a set of characteristic parameters for the non-designed coal type; acquiring a high-temperature corrosion model of the boiler and performing coupled prediction on the high-temperature corrosion model to determine a risk warning scheme, wherein the risk warning scheme includes at least different risk levels, risk thresholds corresponding to different risk levels, and alarm modes; determining a combustion control model through experiments on the thermal / fuel-type NOx formation mechanism; constructing a coal ash melting point prediction model based on the set of characteristic parameters for the non-designed coal type; and generating a coal usage guidance scheme based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, wherein the coal usage guidance scheme includes at least coal purchase guidance data, coal yard blending guidance data, and burner adjustment guidance data. This method proactively prevents risks in key areas, provides precise guidance for coal purchase and usage, and enables real-time monitoring of the combustion status within the furnace.

Description

Technical Field

[0001] This invention relates to the field of combustion optimization technology for thermal power boilers, specifically to the technical field of providing a method and system for combustion optimization of boilers with non-designed coal types based on multi-field coupled simulation. Background Technology

[0002] With the rapid development of renewable energy, thermal power plants need to undertake deep peak-shaving tasks. Boilers are often operating at low to medium loads of 40%-50%, deviating from the design conditions, resulting in a significant drop in efficiency and serious energy waste. At the same time, in pursuit of economic benefits, power plants burn non-design coal types such as high-sulfur and high-ash coal, which further leads to a series of problems: boilers are prone to flameout and pollutant emissions exceed standards under low loads, while water-cooled walls suffer from high-temperature corrosion and severe coking in the furnace under high loads. Among these, unplanned shutdowns caused by water-cooled wall tube ruptures account for 37.8%.

[0003] The existing technology has the following problems: 1) Combustion condition monitoring relies on the detection of flue gas composition in the tail flue, which is far from the main combustion zone. The data is lagging and has low accuracy, and cannot reflect the combustion status in the furnace in real time. 2) Operation control lacks effective technical support and relies on manual experience for adjustment, making it difficult to cope with changes in coal type and load fluctuations. Problems such as coking and high-temperature corrosion can only be dealt with passively. 3) There is a lack of systematic solutions for key technologies such as low-load stable combustion, coordinated control of pollutants, and high-temperature corrosion prevention and control, which cannot meet the synergistic requirements of ultra-low emissions and deep peak shaving.

[0004] Accordingly, there is a need in this field for a new combustion optimization scheme for boilers with undesigned coal types based on multi-field coupled simulation to solve the above problems. Summary of the Invention

[0005] To overcome the above-mentioned shortcomings, this invention is proposed to provide a combustion optimization method and system for non-design coal type boilers based on multi-field coupled simulation, which solves or at least partially solves the technical problems of the inability to monitor combustion conditions, lack of real-time feedback in operation control, and inability to meet the synergistic requirements of ultra-low emissions and deep peak shaving in the prior art.

[0006] In a first aspect, the present invention provides a method for optimizing the combustion of a non-design coal type boiler based on multi-field coupled simulation, the method comprising the following steps: Obtain the characteristic parameter set of non-design coal types; A high-temperature corrosion model of the boiler is obtained, and the high-temperature corrosion model of the boiler is coupled and predicted to determine a risk warning scheme. The risk warning scheme includes at least different risk levels, risk thresholds corresponding to different risk levels, and alarm modes. A combustion control model was determined through experiments on the formation mechanism of thermal / fuel NOx. A coal ash melting point prediction model is constructed based on the characteristic parameter set of non-designed coal types. Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, a coal use guidance scheme is generated. The coal use guidance scheme includes at least coal purchase guidance data, coal yard blending guidance data, and burner adjustment guidance data.

[0007] In one technical solution of the above-mentioned boiler combustion optimization method based on multi-field coupled simulation for non-designed coal types, the acquisition of the characteristic parameter set of the non-designed coal type includes: Obtain data on non-designed coal types, which must include at least volatile matter, ash content, and calorific value. Obtain boiler data; Combustion experiments were conducted on non-designed coal types to obtain a combination of coal type experimental parameters, which included at least the ignition temperature and the burnout temperature. By substituting boiler data and non-design coal type data into the minimum stable combustion load prediction model, the combination of stable combustion parameters for each coal type is obtained. Based on the combination of experimental parameters and the combination of stable combustion parameters for coal types, a set of characteristic parameters for non-designed coal types is obtained.

[0008] In one technical solution of the above-mentioned combustion optimization method for non-design coal type boilers based on multi-field coupled simulation, the acquisition of the high-temperature corrosion model of the boiler includes: Obtain boiler data; Based on boiler data, a three-dimensional model of the furnace is constructed. The water-cooled wall environment of the furnace is simulated to obtain the corrosion product parameter set and the furnace water-cooled wall coupling model, thus obtaining the high-temperature corrosion model of the boiler.

[0009] In one technical solution of the above-mentioned combustion optimization method for non-design coal type boilers based on multi-field coupled simulation, the coupling prediction of the boiler's high-temperature corrosion model to determine the risk warning scheme includes: Temperature and stress fields are applied to the high-temperature corrosion model of the boiler to calculate the predicted rate of pipe wall thinning. By coupling the high-temperature corrosion model of the boiler with the EDC combustion model and the P1 radiation model, the simulated concentration distribution parameters of H2S / CO were obtained. Based on the predicted rate of pipe wall thinning and the simulated concentration distribution parameters of H2S / CO, different risk levels and the corresponding risk thresholds for different risk levels are determined. Based on different risk levels, determine the alarm mode corresponding to each risk level; Based on different risk levels, the corresponding risk thresholds, and the alarm modes for each risk level, a risk warning plan is determined.

[0010] In one technical solution of the above-mentioned combustion optimization method for non-design coal type boilers based on multi-field coupled simulation, the step of determining the combustion control model through thermal / fuel NOx formation mechanism experiments includes: Acquire preset operating condition data, which includes at least the operating parameters such as load and air-to-coal ratio; Based on preset data of different operating conditions, a quantitative test of the formation characteristics mechanism of thermal NOx and fuel NOx was performed using a flue gas analyzer to obtain the formation parameters of thermal NOx and fuel NOx. Obtain combustion data corresponding to different preset operating conditions, and construct an air-stage combustion model based on the combustion data; Based on preset data of different operating conditions and the generation parameters of thermal NOx and fuel NOx, the preset LSTM ammonia injection prediction model is optimized to obtain the optimized LSTM ammonia injection prediction model. The combustion control model is obtained by integrating and optimizing the LSTM ammonia injection prediction model and the air staged combustion model through the DCS system.

[0011] In one technical solution of the above-mentioned combustion optimization method for non-design coal type boilers based on multi-field coupled simulation, the step of obtaining combustion data corresponding to preset different operating conditions and constructing an air-staged combustion model based on the combustion data includes: Obtain combustion data corresponding to different preset operating conditions, wherein the combustion data includes at least the oxygen content in the combustion zone; Based on the oxygen content of the combustion zone, the combustion zone is dynamically divided into three combustion zones, which include the main combustion zone, the reduction zone, and the burnout zone. Based on the three combustion zones, air-stage combustion parameters are obtained, which include combustion parameters that match each combustion zone. An air-stage combustion model is constructed based on air-stage combustion parameters.

[0012] In one technical solution of the above-mentioned boiler combustion optimization method based on multi-field coupled simulation for non-designed coal types, the construction of a coal ash melting point prediction model based on the characteristic parameter set of non-designed coal types includes: A BP neural network is constructed based on the characteristic parameter set of non-designed coal types. Acquire training data, which includes a preset number of gray component-ash melting point data sets; The BP neural network was trained based on the training data to obtain a coal ash melting point prediction model.

[0013] In one technical solution of the above-mentioned non-design coal type boiler combustion optimization method based on multi-field coupled simulation, the generation of coal use guidance scheme based on risk early warning scheme, combustion control model, and coal ash melting point prediction model includes: Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, coal purchase guidance data is determined. The coal purchase guidance data shall include at least the parameter range of different parameter types corresponding to different coal purchase priorities. Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, coal yard blending guidance data is determined, which includes at least the blending ratio. Based on coal yard blending guidance data and coal purchase guidance data, multiple sets of blending parameters for non-designed coal types are obtained. Among them, the blending parameters include at least the coal type parameters and coal type blending ratios for non-designed coal types. Based on multiple sets of blending parameters for non-designed coal types and a combustion control model, combustion prediction parameters are dynamically adjusted to obtain burner parameters corresponding to each set of blending parameters, thereby obtaining burner adjustment guidance data.

[0014] In one technical solution of the above-mentioned combustion optimization method for non-design coal type boilers based on multi-field coupled simulation, the method further includes: Obtain real-time combustion status parameters for coal types; The visualization implementation module generates three-dimensional temperature field and gas concentration field cloud maps of the furnace based on the real-time combustion status of the coal type. Based on real-time combustion state parameters of coal, the coal ash melting point prediction model is selectively adjusted. In response to the adjustment of the coal ash melting point prediction model, the coal use guidance scheme is updated based on the adjusted coal ash melting point prediction model, risk warning scheme, and combustion control model.

[0015] In a second aspect, the present invention provides a combustion optimization system for a non-designed coal type boiler based on multi-field coupled simulation. The system includes a communication device, a data acquisition device, a model building module, and a control device. The data acquisition device is used to acquire a set of characteristic parameters of the non-designed coal type and boiler data. The communication device is used to realize information interaction between the data acquisition device and the system. The model building module is used to construct a high-temperature corrosion model, a combustion control model, and a coal ash melting point prediction model for the boiler. The control device includes a processor and a storage device. The storage device is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to execute the combustion optimization method for a non-designed coal type boiler based on multi-field coupled simulation as described in any of the above-mentioned technical solutions.

[0016] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects: By setting up a risk warning scheme, namely a high-temperature corrosion warning, risks in key parts are prevented in advance, extending the service life of water-cooled walls and improving boiler operation safety. By setting up a combustion control model, combustion optimization and NOx and SCR linkage control are achieved, effectively controlling pollutant emissions, meeting ultra-low emission requirements, and solving the problems of difficult NOx control and ammonia escape under low load. By constructing a coal ash melting point prediction model, the prediction of coking in the furnace is incorporated, and based on the prediction results, a coal use guidance plan is generated to facilitate precise guidance for coal purchase and use in power plants. The coal yard management module of the project power plant is improved, realizing integrated control of the entire coal combustion process of the power plant. Through the visualization implementation module, real-time observation of the combustion status in the furnace is realized, breaking through the limitations of traditional tail-end monitoring, forming a systematic technical solution for deep peak shaving of non-design coal types. This provides technical support for thermal power to adapt to the energy structure transformation and has broad promotion value. In this way, stable combustion without oil injection under low load is achieved, significantly reducing unplanned shutdown accidents such as fire extinguishing, tube rupture, and coking. This saves combustion support costs and grid compensation benefits, saves indirect costs such as maintenance and start-up, and reduces the labor intensity of operators. Attached Figure Description

[0017] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein: Figure 1 This is a schematic diagram of the main steps of a combustion optimization method for non-design coal type boilers based on multi-field coupled simulation according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating a combustion optimization method for non-design coal type boilers based on multi-field coupled simulation according to an embodiment of the present invention. Figure 3 This is a schematic diagram of the main structure of a non-design coal type boiler combustion optimization system based on multi-field coupling simulation according to an embodiment of the present invention.

[0018] List of reference numerals in the attached diagram: 300: Combustion optimization system for boilers with non-designed coal types; 301: Control device; 3011: Processor; 3012: Memory; 3013: Program code; 302: Communication device; 303: Data acquisition device; 304: Model building module. Detailed Implementation

[0019] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0020] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0021] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a combustion optimization method for non-design coal type boilers based on multi-field coupled simulation according to an embodiment of the present invention. Figure 1 As shown, the combustion optimization method for non-design coal type boilers based on multi-field coupled simulation in this embodiment of the invention mainly includes the following steps S101-S105.

[0022] Step S101: Obtain the characteristic parameter set of non-design coal types; Specifically, obtaining the characteristic parameter set of non-designed coal types includes: Obtain data on non-designed coal types, which must include at least volatile matter, ash content, and calorific value. Obtain boiler data; Combustion experiments were conducted on non-designed coal types to obtain a combination of coal type experimental parameters, which included at least the ignition temperature and the burnout temperature. By substituting boiler data and non-design coal type data into the minimum stable combustion load prediction model, the combination of stable combustion parameters for each coal type is obtained. Based on the combination of experimental parameters and the combination of stable combustion parameters for coal types, a set of characteristic parameters for non-designed coal types is obtained.

[0023] Specifically, the formula for the minimum stable fuel load prediction model is as follows: In the formula, Represents the probability of stable combustion. , , , All represent regression coefficients, which were calibrated using experimental data from 100 coal samples, and the coefficient of determination R² ≥ 0.9. The representative coal sample has no ash-based volatile matter content after drying. This represents the ash content of a coal sample on a dry basis. This represents the lower heating value of the coal sample received.

[0024] In the above embodiments, by combining the combustion composition of non-designed coal types with the furnace type, the combustion, ignition, and NOx release characteristics of the coal type are obtained. The minimum ignition conditions of pulverized coal airflow are calculated, and the experimental parameter combination and stable combustion parameter combination of coal types that meet the requirements of stable combustion in the furnace for inferior coal types are obtained, namely the minimum heat load and primary and secondary air operating parameters. This is to avoid the occurrence of fire extinguishing and pollutant exceeding the standard under low load, and to provide guidance for subsequent coal type selection. This achieves an accurate evaluation of the combustion characteristics of inferior coal under deep peak shaving and extremely low load conditions.

[0025] Step S102: Obtain the high-temperature corrosion model of the boiler, and perform coupled prediction on the high-temperature corrosion model of the boiler to determine the risk warning scheme. The risk warning scheme shall include at least different risk levels, risk thresholds corresponding to different risk levels, and alarm modes. Specifically, obtaining the high-temperature corrosion model of the boiler includes: Obtain boiler data; Based on boiler data, a three-dimensional model of the furnace is constructed. The water-cooled wall environment of the furnace is simulated to obtain the corrosion product parameter set and the furnace water-cooled wall coupling model, thus obtaining the high-temperature corrosion model of the boiler.

[0026] Specifically, in some embodiments, constructing a three-dimensional furnace model based on boiler data includes: A 3D furnace model was built using ANSYS Fluent software. Specific parameters were set as follows: a hybrid structured / unstructured mesh with a mesh size of 10 mm and a mesh count ≥ 1 million; the y+ value was ≤ 30 to meet the requirements of the turbulence model. The chemical reaction of pulverized coal combustion was described using an EDC combustion model, and heat radiation transfer was calculated using a P1 radiation model. The two models were coupled to simulate the H2S / CO concentration distribution with a time step of 0.01 s and an iterative convergence standard residual ≤ 10. -5 The boundary conditions are set as follows: inlet primary and secondary air velocities: primary air 25 m / s, secondary air 35 m / s; temperature: primary air 200℃, secondary air 300℃; outlet pressure boundary is set; the result generates distribution cloud maps of H2S concentration in the furnace cross section, with a value range of 0-5000 ppm and CO concentration, with a value range of 0-2000 ppm, and identifies high concentration areas of reducing gas H2S.

[0027] Specifically, the coupled model of the furnace water-cooled wall is expressed by the following formula: In the formula, Represents the corrosion rate of the pipe wall. This represents a constant, which is taken as 1.2 here. 10 -4 , Represents H2S concentration. Represents activation energy. Represents the gas constant. This represents the absolute temperature of the pipe wall.

[0028] In the above embodiments, the working temperature environment of the water-cooled wall is simulated by a tubular furnace, and the working atmosphere environment of the combustion zone is simulated by a gas distribution method. The high-temperature corrosion behavior of the water-cooled wall tube material is tested, and the change curve of corrosion weight gain over time is obtained by fitting. A high-temperature corrosion kinetic model is also given, which realizes the digital representation of the corrosion status of the furnace water-cooled wall and provides a theoretical basis for timely risk warning.

[0029] Specifically, the coupled prediction of the high-temperature corrosion model of the boiler to determine the risk warning scheme includes: Temperature and stress fields are applied to the high-temperature corrosion model of the boiler to calculate the predicted rate of pipe wall thinning. By coupling the high-temperature corrosion model of the boiler with the EDC combustion model and the P1 radiation model, the simulated concentration distribution parameters of H2S / CO were obtained. Based on the predicted rate of pipe wall thinning and the simulated concentration distribution parameters of H2S / CO, different risk levels and the corresponding risk thresholds for different risk levels are determined. Based on different risk levels, determine the alarm mode corresponding to each risk level; Based on different risk levels, the corresponding risk thresholds, and the alarm modes for each risk level, a risk warning plan is determined.

[0030] Specifically, the different risk levels and the corresponding risk thresholds are as follows: low risk: H2S < 1000 ppm; medium risk: H2S between 1000-3000 ppm; high risk: H2S > 3000 ppm. The setting of the risk thresholds here is only an example, and those skilled in the art can set them according to actual usage needs, which will not be elaborated here.

[0031] Specifically, the alarm mode corresponding to each risk level can be one or more of the following: sound alarm, light alarm, and mobile APP push. The alarm mode settings here are only illustrative examples. Those skilled in the art can set them according to actual usage needs, and will not be elaborated here.

[0032] In the above embodiments, by combining the numerical simulation results of the combustion zone in the furnace, a calculation model for the pipe wall thickness under different loads for non-designed coal types is built. The service life of the water-cooled wall pipes is initially estimated, and the safe pipe wall thickness and operating time to ensure the safe operation of the boiler are given. This realizes that high-temperature corrosion early warning can prevent and control risks in key parts in advance, extend the service life of the water-cooled wall, and improve the safety of boiler operation.

[0033] Step S103: Determine the combustion control model through experiments on the formation mechanism of thermal / fuel NOx; Specifically, the determination of the combustion control model through experiments on the thermal / fuel NOx formation mechanism includes: Acquire preset operating condition data, which includes at least the operating parameters such as load and air-to-coal ratio; Based on preset data of different operating conditions, a quantitative test of the formation characteristics mechanism of thermal NOx and fuel NOx was performed using a flue gas analyzer to obtain the formation parameters of thermal NOx and fuel NOx. Obtain combustion data corresponding to different preset operating conditions, and construct an air-stage combustion model based on the combustion data; Based on preset data of different operating conditions and the generation parameters of thermal NOx and fuel NOx, the preset LSTM ammonia injection prediction model is optimized to obtain the optimized LSTM ammonia injection prediction model. The optimized LSTM ammonia injection prediction model can take preset data of different operating conditions and the generation parameters of thermal NOx and fuel NOx, namely NOx concentration, load, air volume and coal quality parameters, and output the predicted ammonia injection amount corresponding to each operating condition. The combustion control model is obtained by integrating and optimizing the LSTM ammonia injection prediction model and the air staged combustion model through the DCS system.

[0034] Specifically, the LSTM ammonia injection prediction model is obtained through the following formula: In the formula, This represents the ratio of ammonia injection rate to NOx concentration. Represents the Sigmoid function. Represents the output layer weights. Represents the output layer bias. Represents a hidden state. This represents the parameter set at the current moment.

[0035] Specifically, the optimized preset LSTM ammonia injection prediction model includes: input variables are NOx concentration (real-time value + predicted value), unit load (range 40%-100%), total air volume, and coal quality parameters (nitrogen content, ash content, and volatile matter); output variable is ammonia injection rate; model training uses historical operating data (with a time span ≥ 1 year) + real-time data, and data preprocessing includes at least missing value imputation, outlier removal, and normalization; model validation uses cross-validation, ensuring that the root mean square error (RMSE) is ≤ 5 mg / Nm³. 3 .

[0036] Specifically, the combustion control model obtained by integrating and optimizing the LSTM ammonia injection prediction model through the DCS system and the air staged combustion model includes: The specific steps for DCS system integration and dynamic testing are as follows: Data interaction is conducted via the OPC UA protocol. The air-stage combustion model outputs air-coal parameters, namely primary air rate and coal powder fineness. The optimized LSTM ammonia injection prediction model is input with NOx concentration and ammonia slip rate. Furthermore, full-condition testing is performed within a load range of 40%-100%, with a load step of 10%. Each condition is operated stably for 2 hours to verify that NOx emission concentration fluctuation is ≤±10mg / Nm³. 3 Ammonia slip rate ≤ 3 ppm; and when NOx concentration exceeds 50 mg / Nm³. 3 When the ammonia injection rate is adjusted, the NH3 / NOx molar ratio is increased by 0.1, and the secondary air damper opening of the burner is adjusted by ±5% to optimize the combustion air distribution.

[0037] Specifically, DCS system integration and dynamic testing are performed using the following formula: In the formula, This represents the change in control output, i.e., the adjustment amount by the DCS system to the actuators (which could be ammonia injection valves, dampers, etc.), used to dynamically balance NOx emissions and ammonia slip concentration. This represents the coefficient that amplifies the current error. The coefficient representing the cumulative historical error. The coefficient representing the trend of prediction error change represents... Represents the real-time error signal, where, .

[0038] Specifically, the step of acquiring combustion data corresponding to preset different operating conditions and constructing an air-stage combustion model based on the combustion data includes: Obtain combustion data corresponding to different preset operating conditions, wherein the combustion data includes at least the oxygen content in the combustion zone; Based on the oxygen content of the combustion zone, the combustion zone is dynamically divided into three combustion zones, which include the main combustion zone, the reduction zone, and the burnout zone. Based on the three combustion zones, air-stage combustion parameters are obtained, which include combustion parameters that match each combustion zone. An air-stage combustion model is constructed based on air-stage combustion parameters.

[0039] Specifically, the oxygen content of the three combustion zones is as follows: 3-5% in the main combustion zone, 6-8% in the reduction zone, and 4-6% in the burnout zone. The oxygen content settings of the three combustion zones are merely illustrative and can be set by those skilled in the art according to actual usage requirements, and will not be elaborated further here.

[0040] Specifically, the air-staged combustion parameters are as follows: Combustion parameters in the main combustion zone are controlled by a variable frequency fan and a closed-loop PID controller for oxygen content to ensure stable pulverized coal ignition and suppress the formation of fuel-type NOx; combustion parameters in the reduction zone are adjusted by lowering the secondary air nozzle by 100mm and using air-staged baffles to create a strong reducing atmosphere, i.e., a CO concentration of 500-1000ppm, to promote the reduction of NOx to N2; combustion parameters in the burnout zone are dynamically adjusted by using burnout air (OFA) to ensure complete pulverized coal combustion and avoid secondary formation of thermal NOx due to localized high temperatures. Furthermore, the specific steps for lowering the secondary air nozzle by 100mm involve locating the original nozzle position using a laser rangefinder and achieving millimeter-level precision lowering using a robotic arm and displacement sensors.

[0041] In the above embodiments, the problem of difficult-to-control pollutant emissions under deep peak shaving is solved by constructing a combustion optimization adjustment mechanism; in particular, the formation mechanism and subsequent synergistic control of NOx are studied to achieve linkage and joint control with SCR. By constructing a combustion optimization adjustment mechanism, the NOx formation mechanism is studied in depth to achieve linkage and joint control with SCR, thus solving the problem of difficult-to-control NOx and ammonia escape under low load.

[0042] Step S104: Construct a coal ash melting point prediction model based on the characteristic parameter set of non-designed coal types; Specifically, the construction of the coal ash melting point prediction model based on the characteristic parameter set of non-designed coal types includes: A BP neural network is constructed based on the characteristic parameter set of non-designed coal types. Acquire training data, which includes a preset number of gray component-ash melting point data sets; The BP neural network is trained based on the training data to obtain the coal ash melting point prediction model, i.e., the trained BP neural network.

[0043] Specifically, the architecture of the BP neural network is as follows: Input layer: 4 neurons, the input parameter is the mass ratio of gray components, which in this case is the mass ratio of SiO2, Al2O3, Fe2O3, and CaO. Hidden layer: 8 neurons, ReLU activation function, and He normal distribution weight initialization; Output layer: 1 neuron, outputting the predicted ash melting point value; Training data: Includes 100 sets of ash composition-ash melting point data (ash melting point = 1350℃ when SiO2 / Al2O3 = 2.0), using the Adam optimizer (with a learning rate of 0.001) and the mean squared error (MSE) loss function; Validation set: This consists of 20% of the training data. Training is considered successful when the prediction error is ≤ ±5%. It is used to ensure the model's generalization ability.

[0044] Specifically, the construction of the coal ash melting point prediction model includes: The melting characteristics of inferior coal were tested by using an ash melting point measuring instrument to obtain the melting point temperature of the tested coal, including deformation temperature, softening temperature, hemispherical temperature, and flow temperature. The softening temperature is the main indicator for evaluating whether coal ash is prone to coking. Through experimental measurement, the composition of low-quality coal ash was analyzed to obtain the content of major metal oxides in the coal ash. The mathematical relationship between the composition and content of coal ash metal oxides and the ash melting point of the coal type was analyzed and calculated. Based on this mathematical relationship, the composition and content of coal ash were used as the input layer, and the ash melting point temperature was used as the output data. A backpropagation neural network was used to automatically find the connection between neurons in each layer. The result data was normalized to obtain a coal ash ash melting point prediction model.

[0045] In the above embodiments, a coal ash melting point prediction model was built by combining the coal pulverization slagging experiment with the numerical model calculation results, thereby realizing the prevention of coking in the furnace. Based on the prediction results and the actual on-site operation, operation guidance, coal use and coal purchase suggestions were given, thereby improving the coal yard management module of the power plant project and ultimately achieving the goal of integrated control of the entire coal combustion process of the power plant.

[0046] Step S105: Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, generate a coal use guidance scheme, which includes at least coal purchase guidance data, coal yard blending guidance data, and burner adjustment guidance data.

[0047] Specifically, the generation of coal usage guidance schemes based on risk warning schemes, combustion control models, and coal ash melting point prediction models includes: Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, coal purchase guidance data is determined. The coal purchase guidance data shall include at least the parameter range of different parameter types corresponding to different coal purchase priorities. Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, coal yard blending guidance data is determined, which includes at least the blending ratio. Based on coal yard blending guidance data and coal purchase guidance data, multiple sets of blending parameters for non-designed coal types are obtained. Among them, the blending parameters include at least the coal type parameters and coal type blending ratios for non-designed coal types. Based on multiple sets of blending parameters for non-designed coal types and a combustion control model, combustion prediction parameters are dynamically adjusted to obtain burner parameters corresponding to each set of blending parameters, thereby obtaining burner adjustment guidance data.

[0048] Specifically, the coal purchasing guidance data determined based on the risk warning scheme, combustion control model, and coal ash melting point prediction model includes: Obtain a preset coal type database, which stores parameters such as deformation temperature, softening temperature, flow temperature, sulfur content, ash content, and volatile matter for each coal type. Based on a pre-set coal type database, the procurement score for each coal type is determined. The data of each coal type were substituted into the combustion control model and the coal ash melting point prediction model respectively for simulation and prediction, and the simulation data and prediction data of each coal type were obtained. By substituting the simulated and predicted data of each coal type into the risk warning scheme, the risk level of each coal type can be obtained. Based on the risk level and procurement score of each coal type, the purchase priority of each coal type is determined, and the parameter range of different parameter types corresponding to different purchase priorities is obtained to determine the coal purchase guidance data.

[0049] Specifically, the process of determining the procurement score for each coal type based on a pre-set coal type database includes: The procurement score for each coal type is obtained using the following formula: In the formula, Procurement scores representing coal types, Represents the softening temperature. Represents the deformation temperature. Represents the flow temperature. Represents sulfur content. Represents ash content, Represents volatile components.

[0050] Specifically, the process of determining the purchasing priority of each coal type based on its risk level and procurement score, and obtaining the parameter ranges for different parameter types corresponding to different purchasing priorities, includes: If the risk level of the coal type reaches high risk, then the priority for purchasing the coal type is determined to be high risk. If the risk level of the coal type is medium risk, and the procurement score of the coal type is lower than the preset minimum procurement score threshold, i.e., 70 points, then the coal type is determined to be a high-risk procurement priority. If the risk level of the coal type is medium risk, and the purchase score of the coal type exceeds the preset minimum purchase score threshold but is lower than the preset maximum purchase score threshold, i.e., 85 points, then the purchase priority of the coal type is determined to be medium risk, which means that the coal type needs to be blended, and the blending ratio is less than 40% and the combustion parameters need to be adjusted. If the risk level of the coal type is low risk and the procurement score of the coal type exceeds the preset highest procurement score threshold, the coal type is determined to be the priority for procurement of low risk, that is, the coal type is directly procured, or the coal type is blended with other coal types that are in the medium risk category, and the blending ratio is higher than 60%.

[0051] Specifically, the data for determining coal yard blending guidance based on risk warning schemes, combustion control models, and coal ash melting point prediction models includes: Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, combustion prediction is carried out for different proportions of blending schemes to obtain the risk level and predicted ash melting point of different proportions of blending schemes. Based on the risk level and predicted ash melting point of different blending schemes, blending schemes are selectively eliminated or adjusted to obtain coal yard blending guidance data.

[0052] In the above embodiments, by constructing a risk warning scheme, a combustion control model, and a coal ash melting point prediction model, stable combustion of pulverized coal under low load and control of NOx, H2S and CO and prevention of high-temperature corrosion, prediction of ash melting point and prevention of slagging, and prediction of furnace combustion zone are achieved. Furthermore, by analyzing coal composition and determining peak-shaving target load, optimal operation adjustment suggestions are given under the target load, as well as coal purchase guidance data, coal yard blending guidance data, and burner adjustment guidance data, thus realizing combustion optimization adjustment guidance for deep peak shaving of non-designed coal types under ultra-low emission conditions.

[0053] Furthermore, the method also includes: Obtain real-time combustion status parameters for coal types; The visualization implementation module generates three-dimensional temperature field and gas concentration field cloud maps of the furnace based on the real-time combustion status of the coal type. Based on real-time combustion state parameters of coal, the coal ash melting point prediction model is selectively adjusted. In response to the adjustment of the coal ash melting point prediction model, the coal use guidance scheme is updated based on the adjusted coal ash melting point prediction model, risk warning scheme, and combustion control model.

[0054] Specifically, obtaining the real-time combustion state parameters of the coal type includes: Obtain actual operating parameters, which include at least temperature, pressure, flow rate, and concentration; Based on the actual dimensions of the combustion zone of the target boiler, a CFD physical model is constructed to calculate combustion data, which includes at least the concentration distributions of temperature, H2S, CO, O2, and NOx. Obtain field test parameters, which include at least the measured values ​​of burner nozzle temperature and flue gas composition; Based on combustion data and field test parameters, the actual operating parameters are corrected to obtain the real-time combustion status parameters of the coal type.

[0055] Specifically, the step of generating a three-dimensional temperature field and gas concentration field cloud map of the furnace through the visualization implementation module based on the real-time combustion status of the coal type includes: The CFD simulation module generates three-dimensional visualization cloud maps of the furnace temperature field and O2 / CO / NOx concentration field, and uses the Matplotlib library to achieve dynamic rendering, enabling real-time adjustment of multiple parameters and generating a comparison chart of adjustment schemes for real-time comparison. The multiple parameters are load, air volume, and coal quality.

[0056] In the above embodiments, by visually displaying the real-time combustion status of coal, operators can intuitively evaluate the adjustment effect and obtain the actual combustion situation in real time, thereby improving the boiler combustion optimization effect of the present invention for non-designed coal types. This achieves the following without changing the burner structure: ensuring stable combustion without flameout under low load, slowing down high-temperature corrosion of water-cooled walls to prevent tube rupture under high load, melting coal ash in the combustion zone without slag shedding, and reducing NOx emissions at the furnace outlet to within the standard.

[0057] Based on steps S101-S105 above, a risk warning scheme, namely high-temperature corrosion warning, was implemented to prevent and control risks in key components in advance, extend the service life of water-cooled walls, and improve boiler operation safety. A combustion control model was established to optimize combustion and achieve NOx and SCR linkage control, effectively controlling pollutant emissions, meeting ultra-low emission requirements, and solving the problems of difficult NOx control and ammonia escape under low load conditions. A coal ash melting point prediction model was constructed, incorporating predictions of coking conditions in the furnace. Based on the prediction results, a coal usage guidance scheme was generated to facilitate precise guidance for coal purchase and use in the power plant, and to improve the coal yard management module of the power plant project, realizing the power plant's coal combustion... The integrated control of the entire process, through a visualization implementation module, enables real-time observation of the combustion status in the furnace, breaking through the limitations of traditional tail-end monitoring. It forms a systematic technical solution for deep peak shaving of non-designed coal types, providing technical support for thermal power to adapt to the energy structure transformation, and has broad promotion value. It also enables stable combustion without oil injection under low load, significantly reducing unplanned shutdown accidents such as fire extinguishing, tube rupture, and coking. This saves combustion-supporting costs and grid compensation benefits, reduces indirect costs such as maintenance and startup, and reduces the labor intensity of operators. It avoids the technical problems of existing technologies, such as the inability to monitor combustion conditions, lack of real-time feedback in operation control, and inability to meet the synergistic requirements of ultra-low emissions and deep peak shaving.

[0058] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0059] Furthermore, the present invention also provides a combustion optimization system for non-design coal type boilers based on multi-field coupled simulation.

[0060] See appendix Figure 3 , Figure 3 This is a main structural block diagram of a combustion optimization system for a non-designed coal type boiler based on multi-field coupled simulation according to an embodiment of the present invention. Figure 3As shown, the non-designed coal type boiler combustion optimization system 300 based on multi-field coupled simulation in this embodiment of the invention mainly includes a communication device 302, a data acquisition device 303, a model building module 304, and a control device 301. The data acquisition device 303 is used to acquire the characteristic parameter set of non-designed coal types and boiler data. The communication device 302 is used to realize information interaction between the data acquisition device 303 and the system. The model building module 304 is used to construct a high-temperature corrosion model, a combustion control model, and a coal ash melting point prediction model for the boiler. The control device 301 includes a processor 3011 and a memory 3012. The memory 3012 can be configured to store program code 3013 for executing the non-designed coal type boiler combustion optimization method based on multi-field coupled simulation in the above-described method embodiment. The processor 3011 can be configured to execute the program code 3013 in the memory 3012. The program code 3013 includes, but is not limited to, the program code 3013 for executing the non-designed coal type boiler combustion optimization method based on multi-field coupled simulation in the above-described method embodiment. For ease of explanation, only the parts relevant to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The control device 301 may be a control device comprising various electronic devices.

[0061] Specifically, the communication device 302 can be connected via Wi-Fi, Bluetooth, or wired connection. The choice of communication device 302 here is only an example. Those skilled in the art can choose according to actual usage needs, as long as the communication device 302 can achieve mutual communication connection with the acquisition device 303 and the system, thereby realizing information interaction between the acquisition device 303 and the system. Further details are omitted here.

[0062] Specifically, the acquisition device 303 is also used to acquire non-designed coal type data, boiler data, preset different operating condition data, preset coal type database, actual operating parameters, and field test parameters.

[0063] Specifically, the acquisition device 303 can be various types of sensors installed in the furnace. The sensors include at least a coking rate sensor and a furnace temperature field sensor. Alternatively, it can be an acquisition device 303 connected to an interactive module. The operator inputs coal composition and boiler data through the interactive terminal. The type of acquisition device 303 is not limited. Those skilled in the art can choose according to actual usage needs, as long as the acquisition device 303 can realize boiler data, characteristic parameter set of non-designed coal types, and boiler data. Further details are omitted here.

[0064] In one implementation, the specific function can be described in steps S101-S105.

[0065] The aforementioned non-design coal type boiler combustion optimization system 300 based on multi-field coupled simulation is used to perform... Figure 1 The embodiments of the non-design coal type boiler combustion optimization method based on multi-field coupled simulation shown are similar in technical principle, technical problem solved and technical effect produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the non-design coal type boiler combustion optimization system 300 based on multi-field coupled simulation can be found in the embodiments of the non-design coal type boiler combustion optimization method based on multi-field coupled simulation, and will not be repeated here.

[0066] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0067] Furthermore, the non-design coal type boiler combustion optimization system 300 based on multi-field coupled simulation of the present invention also includes a computer-readable storage medium. In one embodiment of the present invention, the computer-readable storage medium can be configured to store program code 3013 for executing the non-design coal type boiler combustion optimization method based on multi-field coupled simulation of the above-described method embodiments. This program code 3013 can be loaded and run by a processor 3011 to implement the above-described non-design coal type boiler combustion optimization method based on multi-field coupled simulation. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a memory device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0068] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0069] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0070] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for non-design coal boiler combustion optimization based on multi-field coupling simulation, characterized in that, The method includes the following steps: Obtain the characteristic parameter set of non-design coal types; A high-temperature corrosion model of the boiler is obtained, and the high-temperature corrosion model of the boiler is coupled and predicted to determine a risk warning scheme. The risk warning scheme includes at least different risk levels, risk thresholds corresponding to different risk levels, and alarm modes. A combustion control model was determined through experiments on the formation mechanism of thermal / fuel NOx. A coal ash melting point prediction model is constructed based on the characteristic parameter set of non-designed coal types. Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, a coal use guidance scheme is generated. The coal use guidance scheme includes at least coal purchase guidance data, coal yard blending guidance data, and burner adjustment guidance data.

2. The non-design coal boiler combustion optimization method based on multi-field coupling simulation according to claim 1, characterized in that, The acquisition of the characteristic parameter set of non-designed coal types includes: Obtain data on non-designed coal types, which must include at least volatile matter, ash content, and calorific value. Obtain boiler data; Combustion experiments were conducted on non-designed coal types to obtain a combination of coal type experimental parameters, which included at least the ignition temperature and the burnout temperature. By substituting boiler data and non-design coal type data into the minimum stable combustion load prediction model, the combination of stable combustion parameters for each coal type is obtained. Based on the combination of experimental parameters and the combination of stable combustion parameters for coal types, a set of characteristic parameters for non-designed coal types is obtained.

3. The multi-field coupling simulation based non-design coal boiler combustion optimization method according to claim 2, characterized in that, The process of obtaining the high-temperature corrosion model of the boiler includes: Obtain boiler data; Based on boiler data, a three-dimensional model of the furnace is constructed. The water-cooled wall environment of the furnace is simulated to obtain the corrosion product parameter set and the furnace water-cooled wall coupling model, thus obtaining the high-temperature corrosion model of the boiler.

4. The non-design coal boiler combustion optimization method based on multi-field coupling simulation according to claim 3, characterized in that, The coupled prediction of the high-temperature corrosion model of the boiler to determine the risk warning scheme includes: Temperature and stress fields are applied to the high-temperature corrosion model of the boiler to calculate the predicted rate of pipe wall thinning. By coupling the high-temperature corrosion model of the boiler with the EDC combustion model and the P1 radiation model, the simulated concentration distribution parameters of H2S / CO were obtained. Based on the predicted rate of pipe wall thinning and the simulated concentration distribution parameters of H2S / CO, different risk levels and the corresponding risk thresholds for different risk levels are determined. Based on different risk levels, determine the alarm mode corresponding to each risk level; Based on different risk levels, the corresponding risk thresholds, and the alarm modes for each risk level, a risk warning plan is determined.

5. The multi-field coupling simulation based non-design coal boiler combustion optimization method according to claim 1, characterized in that, The combustion control model determined through experiments on the formation mechanism of thermal / fuel-based NOx includes: Acquire preset operating condition data, which includes at least the operating parameters such as load and air-to-coal ratio; Based on preset data of different operating conditions, a quantitative test of the formation characteristics mechanism of thermal NOx and fuel NOx was performed using a flue gas analyzer to obtain the formation parameters of thermal NOx and fuel NOx. Obtain combustion data corresponding to different preset operating conditions, and construct an air-stage combustion model based on the combustion data; Based on preset data of different operating conditions and the generation parameters of thermal NOx and fuel NOx, the preset LSTM ammonia injection prediction model is optimized to obtain the optimized LSTM ammonia injection prediction model. The combustion control model is obtained by integrating and optimizing the LSTM ammonia injection prediction model and the air staged combustion model through the DCS system.

6. The non-design coal boiler combustion optimization method based on multi-field coupling simulation according to claim 5, characterized in that, The step of acquiring combustion data corresponding to preset different operating conditions and constructing an air-stage combustion model based on the combustion data includes: Obtain combustion data corresponding to different preset operating conditions, wherein the combustion data includes at least the oxygen content in the combustion zone; Based on the oxygen content of the combustion zone, the combustion zone is dynamically divided into three combustion zones, which include the main combustion zone, the reduction zone, and the burnout zone. Based on the three combustion zones, air-stage combustion parameters are obtained, which include combustion parameters that match each combustion zone. An air-stage combustion model is constructed based on air-stage combustion parameters.

7. The multi-field coupling simulation based non-design coal boiler combustion optimization method according to claim 1, characterized in that, The coal ash melting point prediction model constructed based on the characteristic parameter set of non-designed coal types includes: A BP neural network is constructed based on the characteristic parameter set of non-designed coal types. Acquire training data, which includes a preset number of gray component-ash melting point data sets; The BP neural network was trained based on the training data to obtain a coal ash melting point prediction model.

8. The non-design coal boiler combustion optimization method based on multi-field coupling simulation according to claim 7, characterized in that, The coal consumption guidance scheme generated based on the risk warning scheme, combustion control model, and coal ash melting point prediction model includes: Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, coal purchase guidance data is determined. The coal purchase guidance data shall include at least the parameter range of different parameter types corresponding to different coal purchase priorities. Based on the risk warning scheme, combustion control model, and coal ash melting point prediction model, coal yard blending guidance data is determined, which includes at least the blending ratio. Based on coal yard blending guidance data and coal purchase guidance data, multiple sets of blending parameters for non-designed coal types are obtained. Among them, the blending parameters include at least the coal type parameters and coal type blending ratios for non-designed coal types. Based on multiple sets of blending parameters for non-designed coal types and a combustion control model, combustion prediction parameters are dynamically adjusted to obtain burner parameters corresponding to each set of blending parameters, thereby obtaining burner adjustment guidance data.

9. The multi-field coupling simulation based non-design coal boiler combustion optimization method according to claim 8, characterized in that, The method further includes: Obtain real-time combustion status parameters for coal types; The visualization implementation module generates three-dimensional temperature field and gas concentration field cloud maps of the furnace based on the real-time combustion status of the coal type. Based on real-time combustion state parameters of coal, the coal ash melting point prediction model is selectively adjusted. In response to the adjustment of the coal ash melting point prediction model, the coal use guidance scheme is updated based on the adjusted coal ash melting point prediction model, risk warning scheme, and combustion control model.

10. A non-design coal boiler combustion optimization system based on multi-field coupling simulation, characterized in that, The system includes a communication device, a data acquisition device, a model building module, and a control device. The data acquisition device is used to acquire a set of characteristic parameters of non-designed coal types and boiler data. The communication device is used to realize information interaction between the data acquisition device and the system. The model building module is used to construct a high-temperature corrosion model, a combustion control model, and a coal ash melting point prediction model for the boiler. The control device includes a processor and a memory. The memory is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to execute the non-designed coal type boiler combustion optimization method based on multi-field coupled simulation as described in any one of claims 1 to 9.

Images