Boiler thermal deviation prediction model determination method and device, equipment and storage medium

Abstract

The invention discloses a boiler thermal deviation prediction model determination method and device, electronic equipment and a storage medium. According to the technical scheme, by simulating the heat transfer process of the target boiler, the boiler simulation model composed of the combustion model, the water-cooled wall heat transfer model and the water-cooled wall in-tube water power model is determined, and a large amount of temperature simulation data of the superheater wall surface preset point location under different boiler operation data can be obtained through the boiler simulation model; and training the to-be-trained boiler thermal deviation prediction model to obtain the boiler thermal deviation prediction model, thereby solving the problems of large sample data demand of the existing online monitoring boiler thermal deviation prediction model and long time consumption of the numerical simulation boiler thermal deviation model. Through the boiler thermal deviation prediction model, rapid and accurate boiler thermal deviation real-time prediction can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of boiler thermal deviation, and in particular to a method, device, equipment and storage medium for determining a boiler thermal deviation prediction model. Background Art

[0002] Boiler thermal deviation refers to the phenomenon that in the heating surface tubes working in parallel, due to uneven structure, uneven heat absorption and uneven working fluid flow, the working fluid in different tubes absorbs different amounts of heat, resulting in temperature difference, that is, the difference in heat absorption by different heating surface tubes in the boiler.

[0003] Boiler thermal deviation is one of the important factors affecting the safe and economic operation of boilers. Accurate monitoring and calculation of boiler thermal deviation is of great significance for ensuring safe and stable operation of boilers, improving boiler efficiency and reducing operating costs. With the continuous improvement of industrial automation and informatization, boiler thermal deviation monitoring and calculation technology has also made significant progress.

[0004] Traditional methods for determining boiler thermal deviation prediction models include thermocouple measurement, infrared thermal imaging technology, and online calculation technology of furnace wall temperature. These methods are susceptible to environmental influences such as high temperature and corrosion, and have slow response speeds. In addition, the accuracy of thermal deviation measurement is greatly affected by environmental factors, and has high requirements for emissivity. The model is complex to establish and requires a large amount of historical data and prior knowledge.

[0005] Therefore, a method for determining a boiler thermal deviation prediction model is needed to achieve fast and accurate boiler combustion thermal deviation prediction. Summary of the invention

[0006] The present invention provides a method, device, equipment and storage medium for determining a boiler thermal deviation prediction model, so as to realize fast and accurate real-time prediction of boiler thermal deviation.

[0007] In a first aspect, an embodiment of the present invention provides a method for determining a boiler thermal deviation prediction model, the method comprising:

[0008] Determine a boiler simulation model of a target boiler, wherein the boiler simulation model includes a combustion model, a water-cooled wall heat transfer model, and a water-cooled wall tube hydrodynamic model;

[0009] Input at least one set of boiler operation data into the boiler simulation model, and output corresponding temperature simulation data of preset points on the superheater wall; the boiler operation data includes boiler parameters and hydrodynamic parameters;

[0010] The boiler operation data and the temperature simulation data are used as sample data to train the boiler thermal deviation prediction model to be trained, so as to obtain the boiler thermal deviation prediction model.

[0011] In a second aspect, an embodiment of the present invention further provides a device for determining a boiler thermal deviation prediction model, the device comprising:

[0012] A boiler simulation model determination module is used to determine a boiler simulation model of a target boiler, wherein the boiler simulation model includes a combustion model, a water-cooled wall heat transfer model, and a water-cooled wall tube hydrodynamic model;

[0013] A sample data determination module is used to input at least one set of boiler operation data into a boiler simulation model, and output temperature simulation data of a corresponding preset point on the superheater wall; the boiler operation data includes boiler parameters and hydrodynamic parameters;

[0014] The boiler thermal deviation prediction model determination module is used to train the boiler thermal deviation prediction model to be trained by using the boiler operation data and the temperature simulation data as sample data to obtain the boiler thermal deviation prediction model.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for determining a boiler thermal deviation prediction model as described in any one of the embodiments of the present invention is implemented.

[0016] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute a method for determining a boiler thermal deviation prediction model as described in any one of the embodiments of the present invention.

[0017] The technical solution of the embodiment of the present invention simulates the heat transfer process of the target boiler to determine the boiler simulation model composed of the combustion model, the water-cooled wall heat transfer model and the water-cooled wall tube hydrodynamic model. The boiler simulation model can obtain a large amount of temperature simulation data of preset points on the superheater wall under different boiler operation data, and train the boiler thermal deviation prediction model to be trained to obtain the boiler thermal deviation prediction model, which solves the current problems of large sample data demand for online monitoring of boiler thermal deviation prediction models and long time-consuming numerical simulation of boiler thermal deviation models. The boiler thermal deviation prediction model can achieve fast and accurate real-time prediction of boiler thermal deviations.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a flow chart of a method for determining a boiler thermal deviation prediction model provided in the first embodiment of the present invention;

[0021] Figure 2 It is a structural schematic diagram of a device for determining a boiler thermal deviation prediction model provided in Embodiment 2 of the present invention;

[0022] Figure 3 It is a structural schematic diagram of an electronic device for implementing a method for determining a boiler thermal deviation prediction model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Embodiment 1

[0026] Figure 1A flowchart of a method for determining a boiler thermal deviation prediction model is provided for the first embodiment of the present invention. This embodiment is applicable to the determination of a boiler thermal deviation prediction model. The method can be performed by a device for determining a boiler thermal deviation prediction model. The device for determining a boiler thermal deviation prediction model can be implemented in the form of hardware and / or software. The device for determining a boiler thermal deviation prediction model can be configured in any electronic device with network communication and computing. Figure 1 As shown, the method includes:

[0027] S110, determining a boiler simulation model of a target boiler, wherein the boiler simulation model includes a combustion model, a water-cooled wall heat transfer model, and a water-cooled wall tube hydrodynamic model.

[0028] In this embodiment, the boiler simulation model is a simulation model obtained by modeling an actual boiler. In practical applications, the boiler simulation model can be obtained by modeling using simulation software according to a CFD (Computational Fluid Dynamics) numerical simulation method.

[0029] It should be noted that the amount of data required for online monitoring of boiler thermal deviations using a pure mechanism model is very large, and the difference between the real-time calculation effect and the actual situation is not easy to correct. Once a deviation occurs, a lot of time is spent on reconstructing the mechanism model. However, pure CFD numerical simulation takes a long time, occupies a lot of computing resources, and cannot simulate boiler combustion in real time.

[0030] In order to solve the problems that CFD numerical simulation of boiler thermal deviation model takes a long time and there is a large demand for online monitoring of boiler thermal deviation data, this embodiment constructs a boiler simulation model of the target boiler so that a large amount of boiler simulation data can be obtained through the boiler simulation model. The boiler simulation data includes boiler operating conditions and boiler thermal deviation data, and the relationship between the boiler operating conditions and the boiler thermal deviation data can be determined based on the boiler simulation data.

[0031] In the process of constructing the existing boiler simulation model, the water-cooled wall heat transfer model and the water-dynamic model in the water-cooled wall tube are taken as a whole, which cannot reflect the heat transfer of the water-cooled wall in the real boiler. This embodiment reflects the heat transfer of the water-cooled wall in the real boiler by constructing a boiler simulation model including a combustion model, a water-cooled wall heat transfer model and a water-dynamic model in the water-cooled wall tube, that is, heat is transferred from the flue gas to the water-cooled wall, and the radiation heat exchange increases the surface temperature of the water-cooled wall, thereby enhancing the convective heat exchange between the water-cooled wall and the flue gas, and the convective heat exchange will affect the temperature distribution inside the water-cooled wall, thereby changing the heat transfer of the water-cooled wall.

[0032] This embodiment comprehensively considers the water-cooled wall heat transfer model and the water dynamic model inside the water-cooled wall tube, integrates the influence of water-side heat transfer and heat exchange, improves the accuracy and comprehensiveness of the numerical simulation of the target boiler, and can improve the prediction accuracy of the boiler thermal deviation prediction model for the boiler thermal deviation from a mechanistic perspective.

[0033] Optionally, the process of determining the boiler simulation model of the target boiler includes:

[0034] According to the boiler structure, a combustion model, a water-cooled wall heat transfer model and a water-cooled wall tube hydrodynamic model are established in a three-dimensional spatial coordinate system;

[0035] The radiation heat flux calculated by the combustion model is used as the boundary condition of the water-cooled wall heat transfer model;

[0036] The water-cooled wall surface temperature calculated by the water-cooled wall heat transfer model is used as the boundary condition of the water dynamic model inside the water-cooled wall tube to obtain the boiler simulation model of the target boiler.

[0037] In this embodiment, the combustion model is used to describe the combustion process of the simulated fuel in the boiler furnace, the water-cooled wall heat transfer model is used to describe the heat transfer process between the simulated water-cooled wall and the high-temperature flue gas in the furnace, and the hydrodynamic model in the water-cooled wall tube is used to describe the heat transfer process between the water-cooled wall tube and the water-steam mixture.

[0038] In this embodiment, the combustion model includes the ignition of the fuel, the combustion reaction, the heat release, the generation of the combustion products, etc. The principle is based on chemical reaction kinetics and fluid mechanics, taking into account the type, properties, particle size distribution of the fuel, the supply, flow rate and distribution of the air, as well as the geometric shape, temperature field and flow field of the furnace, etc., and by establishing the mass conservation equation, energy conservation equation and momentum conservation equation, the concentration distribution of the fuel and oxygen, the temperature distribution and the air flow velocity distribution and other parameters are solved.

[0039] The water-cooled wall heat transfer model is used to simulate the heat transfer process between the water-cooled wall and the high-temperature flue gas in the furnace. Based on the principle of heat transfer, the water-cooled wall heat transfer model can consider factors such as the material properties, geometric structure, flow state of the working fluid in the tube, and the temperature and heat flux density distribution in the furnace. By establishing the heat conduction equation, convection heat transfer equation, and radiation heat transfer equation, the temperature distribution of the water-cooled wall and the heat transfer rate and other parameters can be solved.

[0040] The hydrodynamic model in the water-cooled wall tube mainly simulates the flow state of water or steam-water mixture in the water-cooled wall tube, including the distribution of parameters such as flow velocity, pressure, density, and water evaporation, boiling, etc. Its principle is based on the basic equations of fluid mechanics and thermodynamics, considering the conservation of mass, momentum and energy of the fluid in the tube, and combining the relationship between the physical parameters of water and temperature and pressure, and solving the flow and thermal parameters of the fluid in the tube through numerical calculation methods.

[0041] Specifically, through simplification of the three-dimensional model, including defining the combustion area of ​​the combustion model in the three-dimensional coordinate system, determining the arrangement of the water-cooled wall tubes in the water-cooled wall heat transfer model (in sequence or staggered), tube diameter, tube spacing, tube wall thickness, etc., the space inside the water-cooled wall tube is used as the calculation area, and the grid is divided according to the shape and size of the tube. The grid can be encrypted near the tube wall and in areas where the flow changes dramatically.

[0042] Next, the simulation software is used to define the thermodynamic and transport properties of the fluids involved, such as the flue gas produced by combustion, the water used for cooling, and the steam produced. Select the corresponding fluid material (such as ideal gas, water-steam mixture, etc.) in the material library of the simulation software, and set its properties that change with temperature and pressure, such as density, specific heat capacity, thermal conductivity, viscosity, etc. If the required precise material is not available in the material library, you can also customize the material properties by entering relevant physical property parameters or using user-defined functions to define the relationship between the properties and temperature and pressure. For the solid parts of the boiler, such as metal pipe walls, refractory materials, etc., define their density, thermal conductivity, specific heat capacity and other properties. These properties usually depend on the type of material. You can select the appropriate solid material from the material library, or customize the material properties.

[0043] Then, set the equations of the boiler simulation model. For example, the gas phase-combustion related heat transfer model can use steady-state calculation, turn on the energy equation, select the k-ε model, mixing number-probability density function model, etc. to simulate the turbulent combustion reaction rate according to the actual situation, turn on the radiation heat transfer in the furnace, select the P1 model, etc., and make relevant settings for the particle phase, including the injection parameters of the pulverized coal particles.

[0044] Then, boundary conditions are set, such as air inlet and outlet conditions, and the combustion model, water-cooled wall heat transfer model, and water-cooled wall tube hydrodynamic model are coupled. The combustion model provides boundary conditions such as high-temperature flue gas temperature and flow rate for the water-cooled wall heat transfer model. The tube wall temperature and heat transfer capacity calculated by the water-cooled wall heat transfer model are used as the internal heat source and wall boundary conditions in the hydrodynamic model. The working fluid temperature and flow rate in the hydrodynamic model are fed back to the water-cooled wall heat transfer model to affect its heat transfer characteristics, thus realizing the coupling of the three models: combustion model, water-cooled wall heat transfer model, and water-cooled wall tube hydrodynamic model.

[0045] Finally, the above model equations are discretized using computational fluid dynamics (CFD) software to obtain the boiler simulation model of the target boiler. The discrete equations are solved using an iterative algorithm, and reasonable solution parameters, such as time step and convergence criteria, are set to ensure calculation stability and accuracy. Through multiple iterations of the boiler simulation model, detailed information that can simulate the combustion, heat transfer, and hydrodynamics in the actual boiler is obtained, such as the temperature distribution in the furnace, the cross-sectional air velocity distribution, and other boiler simulation results.

[0046] It should be noted that in the boiler, the principle of radiation heat exchange to the water-cooled wall after coal powder combustion is that the solid particles and gas molecules in the high-temperature flue gas continuously emit and absorb radiation energy, and part of the radiation energy is absorbed by the water-cooled wall, thereby realizing heat transfer.

[0047] Specifically, the radiation heat transfer process of the furnace combustion to the water-cooled wall can be characterized by coupling the combustion model and the water-cooled wall heat transfer model, which can be expressed by the following formula:

[0048]

[0049] Among them, q r is the radiation heat flux density, σ is the Stefan-Boltzmann constant, F is the shape factor (indicating the geometric relationship between the radiation source and the heated surface), T f is the flame temperature, T w is the water-cooled wall surface temperature.

[0050] It should be noted that in simulation software, the energy equation usually takes into account convection and conduction. When building the model, you can add the radiation source term in the user-defined function (UDF), that is, q in the above formula r .

[0051] Optionally, the water wall heat transfer model is expressed by:

[0052]

[0053] Where ρ is the density of the water wall material, c p is the specific heat capacity, T is the water-cooled wall surface temperature, t is the time, k is the thermal conductivity, is the gradient operator and Q is the heat source term.

[0054] In this embodiment, the water-cooled wall heat transfer model adopts a constant heat flux wall, and the heat transfer from the high-temperature gas to the wall is simulated by specifying the heat flux density, such as the constant heat flux wall model, energy conservation, etc. Then the water-cooled wall is regarded as a single medium heat conduction, and its basic heat conduction can be expressed by the above formula, which also describes the heat transfer process of the water-cooled wall heat transfer model.

[0055] Optional. The hydrodynamic model inside the water-cooled wall tube is expressed by the following equation:

[0056]

[0057] Where ρ is the fluid density, c p is the specific heat capacity of the fluid, u is the axial velocity of the fluid, k is the thermal conductivity of the fluid, x is the axial coordinate, r is the radial coordinate, and T is the temperature.

[0058] In this embodiment, the hydrodynamic model in the tube includes a phase change model, a gas-liquid two-phase multiphase flow model, and a turbulence model, etc. When the boiler operating condition is stable, at any point in the wall of the water-cooled tube, the inner wall temperature of the water-cooled tube remains constant, and the fluid has developed into a sufficient laminar flow or turbulent flow after entering the tube section. When only the influence of the inner wall temperature on the fluid is considered, the heat transfer process of the hydrodynamic model in the water-cooled wall tube can be simplified to one-dimensional heat conduction, assuming that heat is only transferred in the radial direction, and ignoring the temperature gradients in the axial and circumferential directions.

[0059] S120, inputting at least one set of boiler operation data into a boiler simulation model, and outputting corresponding temperature simulation data of preset points on the superheater wall.

[0060] In this embodiment, the boiler operation data includes boiler parameters and hydrodynamic parameters. The boiler parameters include the moisture content of the coal type, the volatile matter of the coal type, the ash content of the coal type, the calorific value of the coal type, the fineness of the coal powder, the boiler load, the air distribution method, the air temperature entering the furnace, the excess air coefficient and the opening of each layer of the air door. The hydrodynamic parameters include the feed water flow rate and the feed water pressure.

[0061] The temperature simulation data is the temperature data of the preset points on the superheater wall output by the boiler simulation model according to the boiler operation data. The preset points can be key points that can represent different positions of the boiler outlet or the superheater wall that can represent the difference in heat absorption.

[0062] In this embodiment, the CFD numerical simulation method can be used to input different boiler operation data into the boiler simulation model to simulate the operation results of the boiler under different operating conditions.

[0063] Furthermore, according to different working conditions, the boundary conditions of fuel and air at the burner inlet are set, such as coal moisture, coal volatile matter, coal ash, coal calorific value and coal powder fineness. For the fuel inlet, the mass flow rate, velocity, temperature, particle size distribution and other parameters of the fuel need to be specified. For the air inlet, the air flow rate, velocity, temperature, turbulence intensity, etc., such as boiler load, air distribution method, furnace air temperature, excess air coefficient and each layer of air door opening, etc. need to be set.

[0064] In addition, set the pressure outlet boundary condition at the furnace outlet or flue outlet to specify the outlet pressure value. At the same time, the reflux condition at the outlet can be set as needed to simulate the flue gas reflux phenomenon that may occur in actual operation.

[0065] For the water-cooled wall surface, set the water flow rate, water pressure, and no-slip boundary conditions, that is, the fluid velocity at the wall is zero. At the same time, define the heat transfer conditions between the wall and the working fluid, such as a given wall heat flux or wall temperature. For the insulated wall surface (such as part of the refractory area), set the insulated boundary conditions, that is, the wall heat flux is zero.

[0066] Initialize the flow field in the computational domain, including setting the initial distribution of velocity, temperature, pressure and other parameters. The selection of initial values ​​should be as close as possible to the actual operating conditions to speed up the calculation convergence. For example, the initial furnace temperature and flue gas velocity can be set according to the boiler design parameters or previous experience.

[0067] Furthermore, according to the characteristics of flow and heat transfer in the boiler, a suitable solver is selected. For incompressible flow, a pressure-based solver (such as PISO algorithm, SIMPLE algorithm, etc.) can be selected. For compressible flow, a density-based solver can be selected. For example, in the simulation of high-temperature and high-speed combustion airflow in the furnace, a density-based solver can be used.

[0068] Set the control parameters of the solution, such as the number of iterations, time step (if transient simulation is performed), convergence criteria, etc. The convergence criteria are usually measured by the degree of decrease in residuals, such as setting the residual convergence criteria of the continuity equation, momentum equation, energy equation, etc. to 10 -3 or 10 -4 For steady-state simulation, multiple iterative calculations are performed until the residuals of each physical quantity meet the convergence criteria, and the calculation is considered to have reached a stable solution.

[0069] Start the solver and start the numerical calculation. During the calculation process, pay close attention to the changes in the residual curve, the monitoring point data of the physical quantity, and the use of computing resources. If problems such as residual divergence and non-convergence of calculation occur, you need to adjust the solution parameters, mesh quality or boundary conditions, and recalculate.

[0070] Finally, the simulation results can be displayed in the form of cloud maps, such as temperature cloud maps, velocity cloud maps, pressure cloud maps, etc. Through the cloud maps, the distribution of physical quantities in different areas of the boiler can be intuitively observed, such as the location of the high-temperature area in the furnace, the velocity distribution of the flue gas flow, etc.

[0071] Furthermore, key operating parameters are extracted from the simulation results, such as furnace outlet temperature, heat transfer of the heating surface, temperature and pressure changes of the working fluid in the water-cooled wall tubes, etc. These parameters are crucial for evaluating the performance and operating status of the boiler.

[0072] It should be noted that in this embodiment, the model simulation results can also be compared and verified with the actual operation data to evaluate the accuracy of the boiler simulation model. If there is a deviation between the model simulation results and the actual operation data, the cause can be analyzed and the boiler simulation model can be optimized, such as adjusting the boiler simulation model parameters and improving the boundary condition settings, etc., to improve the accuracy and reliability of the boiler simulation model. By continuously optimizing the boiler simulation model, it can more accurately simulate the operation of the boiler under different working conditions, providing strong support for the design, operation and maintenance of the boiler.

[0073] Optionally, at least one set of boiler operation data is input into the boiler simulation model, and the corresponding temperature simulation data of the preset points on the superheater wall are output, including:

[0074] Meshing the boiler simulation model to obtain node coordinates of each mesh node;

[0075] Performing heat transfer simulation on at least one set of boiler operation data in the meshed boiler simulation model to obtain first temperature simulation data of the superheater wall; the first temperature simulation data includes temperature simulation data of each mesh node;

[0076] Determine a preset point on the wall of the superheater, and determine a target grid node matching the preset point from the grid nodes; the three-dimensional coordinates of the preset point match the node coordinates of the target node;

[0077] According to the node coordinates of the target grid node, the first temperature simulation data is extracted to obtain the temperature simulation data of the preset point on the superheater wall.

[0078] In this embodiment, the first temperature simulation data is the temperature data of the superheater wall under the boiler operation data simulated according to the boiler simulation model. The target grid node is the node on the boiler simulation model that matches the preset point.

[0079] Specifically, the boiler simulation model can be meshed using computational fluid dynamics software. The coordinate information of all mesh nodes is stored in a node file. Each line in the node file represents a node in the format of (x yz), where x, y, and z are the coordinate values ​​of the mesh node in three-dimensional space. The node coordinates of each mesh node can be obtained by reading the mesh node coordinate information stored in the node file through a text editor.

[0080] Through meshing, the continuous solution area of ​​the boiler is discretized into a large number of small units, namely grids. In order to more accurately approximate the solution of control equations such as the mass conservation equation, momentum conservation equation and energy conservation equation in each grid unit, the accuracy of the description of complex physical phenomena in the boiler, such as fluid flow, heat and mass transfer and chemical reactions, can be improved. In addition, after the entire boiler solution area is divided into multiple small grid units, each boiler operation process can be calculated separately on these units, and then coupled and iteratively solved. In this way, the complex overall calculation task can be decomposed into relatively simple subtasks, reducing the scale and difficulty of a single calculation, thereby improving the calculation efficiency and shortening the calculation time.

[0081] Further, heat transfer simulation is performed on at least one set of boiler operation data in the boiler simulation model after meshing to obtain first temperature simulation data. According to the fluid material, solid material, boundary conditions, initialization information, solution parameters, etc. set in the boiler simulation model, the solver is started to perform numerical calculations on the boiler operation data input in the boiler simulation model to obtain the first temperature simulation data corresponding to each set of boiler operation data. In practical applications, temperature simulation data of specific surfaces (such as water-cooled wall surface, heating surface surface, superheater surface, etc.) can be extracted through simulation software.

[0082] Furthermore, a preset point on the superheater wall is determined, and a target grid node matching the preset point is determined from the divided grid nodes, so that the three-dimensional coordinates of the preset point match the node coordinates of the target grid node.

[0083] Specifically, the node coordinates of the grid node can be directly compared with the three-dimensional coordinates of the preset point, and the coordinate difference between the node coordinates of the grid node and the three-dimensional coordinates of the preset point in the X, Y, and Z directions can be calculated to evaluate the degree of deviation between the two. For example, if the coordinates of an actual preset point are (10, 20, 30), and the corresponding grid node coordinates of the boiler simulation model are (10.1, 20.2, 30.3), the deviation values ​​in each direction can be calculated, and the total deviation value can be determined according to the sum of the deviation values ​​in each direction.

[0084] Furthermore, the grid node with a total deviation value less than the preset deviation value may be used as the target grid node matching the preset point, or the grid node with the smallest total deviation value may be used as the target grid node matching the preset point.

[0085] It should be noted that the first temperature simulation data includes the temperature simulation data of each grid node. Further, data extraction can be performed from the first temperature simulation data to determine the temperature simulation data corresponding to the node coordinates of the target grid node as the temperature simulation data of the preset point on the superheater wall.

[0086] S130 , using the boiler operation data and the temperature simulation data as sample data to train a boiler thermal deviation prediction model to be trained, to obtain a boiler thermal deviation prediction model.

[0087] In this embodiment, the temperature simulation data is the corresponding simulation result obtained by performing heat transfer simulation according to each set of boiler operation data through the boiler simulation model.

[0088] It should be noted that the numerical calculation efficiency of the boiler simulation model based on different boiler operating data cannot meet the real-time monitoring of the target boiler operating conditions in actual applications, and cannot ensure the safe and stable operation of the boiler, improve boiler efficiency and reduce operating costs.

[0089] Therefore, according to the simulation results of the above process, a boiler thermal deviation simulation database can be constructed based on each set of boiler operation data and temperature simulation data. Using a large amount of simulation data, a complex boiler thermal deviation prediction model is established to achieve accurate prediction of boiler thermal deviation.

[0090] Since complex boiler thermal deviation prediction models require a large amount of data for training, boilers in actual scenarios react slowly and have low data acquisition efficiency, the boiler operation data input and the temperature simulation data output in the boiler simulation model can be used as sample data to train the boiler thermal deviation prediction model to obtain the boiler thermal deviation prediction model.

[0091] Optionally, the boiler operation data and the temperature simulation data are used as sample data to train a boiler thermal deviation prediction model to be trained, so as to obtain a boiler thermal deviation prediction model, including:

[0092] Using the boiler operation data and the temperature simulation data as sample data, and dividing the sample data into a training set and a test set;

[0093] The training set is used to train the thermal deviation prediction model of the boiler to be trained, so as to obtain the trained thermal deviation prediction model of the boiler to be trained;

[0094] Inputting the boiler operation data of the test set into the trained boiler thermal deviation prediction model to obtain reference temperature data of preset points on the superheater wall;

[0095] The loss value is determined according to the reference temperature data and the temperature simulation data of the test set, and the loss function of the trained boiler thermal deviation prediction model is optimized according to the loss value until the boiler thermal deviation prediction model is obtained by meeting the preset conditions.

[0096] In this embodiment, the sample data includes each group of boiler operation data and corresponding temperature simulation data. The boiler operation data and corresponding temperature simulation data in the training set are used to train the boiler thermal deviation prediction model to be trained, and the boiler operation data and corresponding temperature simulation data in the test set are used to optimize the loss function of the boiler thermal deviation prediction model. The reference temperature data is the output data of the trained boiler thermal deviation model for the input boiler operation data in the test set. The preset condition can be that the loss value is less than the preset loss value threshold or the loss value no longer changes or the number of model training reaches the preset training rounds, etc.

[0097] It should be noted that the boiler thermal deviation prediction model to be trained is a neural network model that can output temperature simulation data according to the input boiler operation data. Commonly used neural network models include convolutional neural network models, multi-layer perceptron models, and recurrent neural network models.

[0098] Furthermore, the correlation between each parameter in the boiler operation data and the temperature simulation data is determined, and the parameter in the boiler operation data that has the greatest impact on the temperature simulation data can be selected as a feature, and the correlation between the parameter and the temperature simulation data is used as the correlation between the boiler operation data and the temperature simulation data. Alternatively, the boiler operation parameters whose correlation between each parameter in the boiler operation data and the temperature simulation data is greater than a preset correlation threshold are selected and input into the boiler thermal deviation prediction model to be trained.

[0099] Furthermore, the boiler operation data in the training set is used as input, and the temperature simulation data in the training set is used as output to train the boiler thermal deviation prediction model for multiple rounds. During the training process, the boiler thermal deviation prediction model to be trained will continuously adjust the weights according to the training data to minimize the loss function. The boiler thermal deviation prediction model after training can be used for subsequent evaluation and actual prediction tasks.

[0100] Furthermore, the boiler operation data of the test set is input into the trained boiler thermal deviation prediction model to be trained, and the reference temperature data of the key points of the superheater wall are obtained. The loss value is determined according to the reference temperature data and the temperature simulation data of the test set, and the loss function of the boiler thermal deviation prediction model to be trained is optimized according to the loss value until the preset conditions are met to obtain the boiler thermal deviation prediction model. During the test process, the loss value is checked cyclically to see whether it meets the preset conditions, such as the loss value is less than 0.01 or the loss value change is less than 0.001 for 5 consecutive rounds. If the conditions are not met, the regularization coefficient is adjusted and the boiler thermal deviation prediction model is continued to be trained until the preset conditions are met to obtain the boiler thermal deviation prediction model.

[0101] In practical applications, after determining the boiler thermal deviation prediction model of the target boiler, the real-time boiler operation data can be connected as the input of the boiler thermal deviation prediction model, and the predicted temperature data can be output by the boiler thermal deviation prediction model to invert the boiler thermal deviation distribution information in real time to improve the safety of boiler monitoring. At the same time, the real-time boiler operation data and the actual temperature data of the preset points on the boiler superheater wall can be used as new data sets to correct the above boiler thermal deviation prediction model, thereby improving the prediction accuracy of the boiler thermal deviation prediction model.

[0102] The technical solution of the embodiment of the present invention simulates the heat transfer process of the target boiler to determine the boiler simulation model composed of the combustion model, the water-cooled wall heat transfer model and the water-cooled wall tube hydrodynamic model. The boiler simulation model can obtain a large amount of temperature simulation data of preset points on the superheater wall under different boiler operation data, and train the boiler thermal deviation prediction model to be trained to obtain the boiler thermal deviation prediction model, which solves the current problems of large sample data demand for online monitoring of boiler thermal deviation prediction models and long time consumption for numerical simulation of boiler thermal deviation models. The boiler thermal deviation prediction model can achieve fast and accurate real-time prediction of boiler thermal deviations.

[0103] Embodiment 2

[0104] Figure 2 This is a schematic diagram of the structure of a device for determining a boiler thermal deviation prediction model provided in Embodiment 3 of the present invention. Figure 2 As shown, the device comprises:

[0105] A boiler simulation model determination module 310 is used to determine a boiler simulation model of a target boiler, wherein the boiler simulation model includes a combustion model, a water-cooled wall heat transfer model, and a water-cooled wall tube hydrodynamic model;

[0106] The sample data determination module 320 is used to input at least one set of boiler operation data into the boiler simulation model, and output the corresponding temperature simulation data of the preset points on the superheater wall; the boiler operation data includes boiler parameters and hydrodynamic parameters;

[0107] The boiler thermal deviation prediction model determination module 330 is used to train the boiler thermal deviation prediction model to be trained by using the boiler operation data and the temperature simulation data as sample data to obtain the boiler thermal deviation prediction model.

[0108] Optionally, the process of determining the boiler simulation model of the target boiler includes:

[0109] A combustion model, a water-cooled wall heat transfer model and a water-dynamic model in a water-cooled wall tube are established in a three-dimensional spatial coordinate system according to the boiler structure; the combustion model is used to describe the combustion process of the simulated fuel in the boiler furnace, the water-cooled wall heat transfer model is used to describe the heat transfer process between the simulated water-cooled wall and the high-temperature flue gas in the furnace; the water-dynamic model in a water-cooled wall tube is used to describe the heat transfer process between the water-cooled wall tube and the water-vapor mixture;

[0110] The radiation heat flux calculated by the combustion model is used as the boundary condition of the water-cooled wall heat transfer model;

[0111] The water-cooled wall surface temperature calculated by the water-cooled wall heat transfer model is used as the boundary condition of the water dynamic model inside the water-cooled wall tube to obtain the boiler simulation model of the target boiler.

[0112] Optionally, the water wall heat transfer model is expressed by:

[0113]

[0114] Among them, ρ is the density of the water-cooled wall material, cp is the specific heat capacity, T is the temperature of the water-cooled wall surface, t is the time, k is the thermal conductivity, is the gradient operator and Q is the heat source term.

[0115] Optionally, the method according to claim 3 is characterized in that the hydrodynamic model inside the water-cooled wall tube is expressed by the following formula:

[0116]

[0117] Among them, ρ is the fluid density, cp is the fluid specific heat capacity, u is the fluid axial velocity, k is the fluid thermal conductivity, x is the axial coordinate, r is the radial coordinate, and T is the temperature.

[0118] Optionally, at least one set of boiler operation data is input into the boiler simulation model, and the corresponding temperature simulation data of the preset points on the superheater wall are output, including:

[0119] Meshing the boiler simulation model to obtain node coordinates of each mesh node;

[0120] Performing heat transfer simulation on at least one set of boiler operation data in the meshed boiler simulation model to obtain first temperature simulation data of the superheater wall; the first temperature simulation data includes temperature simulation data of each mesh node;

[0121] Determine a preset point on the wall of the superheater, and determine a target grid node matching the preset point from the grid nodes; the three-dimensional coordinates of the preset point match the node coordinates of the target node;

[0122] According to the node coordinates of the target grid node, the first temperature simulation data is extracted to obtain the temperature simulation data of the preset point on the superheater wall.

[0123] Optionally, the boiler operation data and the temperature simulation data are used as sample data to train a boiler thermal deviation prediction model to be trained, so as to obtain a boiler thermal deviation prediction model, including:

[0124] Using the boiler operation data and the temperature simulation data as sample data, and dividing the sample data into a training set and a test set;

[0125] The training set is used to train the thermal deviation prediction model of the boiler to be trained, so as to obtain the trained thermal deviation prediction model of the boiler to be trained;

[0126] Inputting the boiler operation data of the test set into the trained boiler thermal deviation prediction model to obtain reference temperature data of preset points on the superheater wall;

[0127] The loss value is determined according to the reference temperature data and the temperature simulation data of the test set, and the loss function of the trained boiler thermal deviation prediction model is optimized according to the loss value until the boiler thermal deviation prediction model is obtained by meeting the preset conditions.

[0128] Optionally, the boiler operation data include boiler parameters and hydrodynamic parameters. The boiler parameters include moisture content of coal, volatile matter of coal, ash content of coal, calorific value of coal, coal powder fineness, boiler load, air distribution method, inlet air temperature, excess air coefficient and air door opening of each layer. The hydrodynamic parameters include feed water flow and feed water pressure.

[0129] The technical solution of the embodiment of the present invention simulates the heat transfer process of the target boiler to determine the boiler simulation model composed of the combustion model, the water-cooled wall heat transfer model and the water-cooled wall tube hydrodynamic model. The boiler simulation model can obtain a large amount of temperature simulation data of preset points on the superheater wall under different boiler operation data, and train the boiler thermal deviation prediction model to be trained to obtain the boiler thermal deviation prediction model, which solves the current problems of large sample data demand for online monitoring of boiler thermal deviation prediction models and long time consumption for numerical simulation of boiler thermal deviation models. The boiler thermal deviation prediction model can achieve fast and accurate real-time prediction of boiler thermal deviations.

[0130] The apparatus for determining a boiler thermal deviation prediction model provided in an embodiment of the present invention can execute the method for determining a boiler thermal deviation prediction model provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0131] Embodiment 3

[0132] Figure 3 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0133] like Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0134] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0135] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a method for determining a boiler thermal deviation prediction model.

[0136] In some embodiments, the method for determining the boiler thermal deviation prediction model may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the boiler thermal deviation prediction model described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the boiler thermal deviation prediction model in any other appropriate manner (e.g., by means of firmware).

[0137] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0139] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0142] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0143] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0144] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a boiler thermal deviation prediction model, characterized in that: include: Determine a boiler simulation model of a target boiler, wherein the boiler simulation model includes a combustion model, a water-cooled wall heat transfer model, and a water-cooled wall tube hydrodynamic model; Input at least one set of boiler operation data into the boiler simulation model, and output corresponding temperature simulation data of preset points on the superheater wall; the boiler operation data includes boiler parameters and hydrodynamic parameters; The boiler operation data and the temperature simulation data are used as sample data to train the boiler thermal deviation prediction model to be trained, so as to obtain the boiler thermal deviation prediction model.

2. The method according to claim 1, characterized in that The process of determining the boiler simulation model of the target boiler includes: A combustion model, a water-cooled wall heat transfer model and a water-dynamic model in a water-cooled wall tube are established in a three-dimensional spatial coordinate system according to the boiler structure; the combustion model is used to describe the combustion process of the simulated fuel in the boiler furnace, the water-cooled wall heat transfer model is used to describe the heat transfer process between the simulated water-cooled wall and the high-temperature flue gas in the furnace; the water-dynamic model in a water-cooled wall tube is used to describe the heat transfer process between the water-cooled wall tube and the water-vapor mixture; The radiation heat flux calculated by the combustion model is used as the boundary condition of the water-cooled wall heat transfer model; The water-cooled wall surface temperature calculated by the water-cooled wall heat transfer model is used as the boundary condition of the water dynamic model inside the water-cooled wall tube to obtain the boiler simulation model of the target boiler.

3. The method according to claim 1, characterized in that The water-cooled wall heat transfer model is expressed by the following formula: Where ρ is the density of the water wall material, c p is the specific heat capacity, T is the water-cooled wall surface temperature, t is the time, k is the thermal conductivity, is the gradient operator and Q is the heat source term.

4. The method according to claim 3, characterized in that The hydrodynamic model inside the water-cooled wall tube is expressed by the following formula: Where ρ is the fluid density, c p is the specific heat capacity of the fluid, u is the axial velocity of the fluid, k is the thermal conductivity of the fluid, x is the axial coordinate, r is the radial coordinate, and T is the temperature.

5. The method according to claim 1, characterized in that At least one set of boiler operation data is input into the boiler simulation model, and the corresponding temperature simulation data of the preset points on the superheater wall are output, including: Meshing the boiler simulation model to obtain node coordinates of each mesh node; Performing heat transfer simulation on at least one set of boiler operation data in the meshed boiler simulation model to obtain first temperature simulation data of the superheater wall; the first temperature simulation data includes temperature simulation data of each mesh node; Determine a preset point on the wall of the superheater, and determine a target grid node matching the preset point from the grid nodes; the three-dimensional coordinates of the preset point match the node coordinates of the target node; According to the node coordinates of the target grid node, the first temperature simulation data is extracted to obtain the temperature simulation data of the preset point on the superheater wall.

6. The method according to claim 1, characterized in that The boiler operation data and the temperature simulation data are used as sample data to train the boiler thermal deviation prediction model to be trained, so as to obtain the boiler thermal deviation prediction model, including: Using the boiler operation data and the temperature simulation data as sample data, and dividing the sample data into a training set and a test set; The training set is used to train the thermal deviation prediction model of the boiler to be trained, so as to obtain the trained thermal deviation prediction model of the boiler to be trained; Inputting the boiler operation data of the test set into the trained boiler thermal deviation prediction model to obtain reference temperature data of preset points on the superheater wall; The loss value is determined according to the reference temperature data and the temperature simulation data of the test set, and the loss function of the trained boiler thermal deviation prediction model is optimized according to the loss value until the boiler thermal deviation prediction model is obtained by meeting the preset conditions.

7. The method according to claim 1, characterized in that The boiler operation data includes boiler parameters and hydrodynamic parameters. The boiler parameters include coal moisture, coal volatile matter, coal ash, coal calorific value, coal powder fineness, boiler load, air distribution method, furnace inlet air temperature, excess air coefficient and each layer of air door opening. The hydrodynamic parameters include feed water flow and feed water pressure.

8. A device for determining a boiler thermal deviation prediction model, characterized in that: include: A boiler simulation model determination module is used to determine a boiler simulation model of a target boiler, wherein the boiler simulation model includes a combustion model, a water-cooled wall heat transfer model, and a water-cooled wall tube hydrodynamic model; A sample data determination module is used to input at least one set of boiler operation data into a boiler simulation model, and output temperature simulation data of a corresponding preset point on the superheater wall; the boiler operation data includes boiler parameters and hydrodynamic parameters; The boiler thermal deviation prediction model determination module is used to train the boiler thermal deviation prediction model to be trained by using the boiler operation data and the temperature simulation data as sample data to obtain the boiler thermal deviation prediction model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for determining the boiler thermal deviation prediction model as described in any one of claims 1-7 is implemented.

10. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to execute the method for determining a boiler thermal deviation prediction model as described in any one of claims 1 to 7.

Images