Method and device for modeling pulverized coal gasifier based on CFD (computational fluid dynamics) reduced-order model

Abstract

The invention discloses a pulverized coal gasifier modeling method and device based on a CFD reduced-order model. Constructing a flow network model of the gasification furnace based on the functional partitions of the gasification furnace, and constructing a chemical reaction model of each functional partition; cFD simulation is carried out based on the flow network model and the chemical reaction model; constructing an order reduction model based on the CFD simulation result and the field experiment data of the gasification furnace; and carrying out hybrid modeling on the reduced-order model and the mechanism model of the gasification furnace to obtain a gasification furnace hybrid model. According to the technical scheme provided by the embodiment of the invention, a multi-disciplinary and multi-dimensional coupling technology is adopted for analogue simulation of the industrial pulverized coal gasifier, so that a high-precision model is realized in a manner of combining mechanism modeling with CFD reduced-order model data correction; and the defects of poor epitaxy and the like caused by structural data missing, mechanism data insufficiency and the like of a traditional pure mechanism model or data model device are overcome, and high-precision simulation of the process is realized.

Description

Technical Field

[0001] The present invention relates to the field of simulation technology, and in particular to a pulverized coal gasification furnace modeling method and device based on a CFD reduced-order model. Background Art

[0002] At present, coal gasification technology is widely used in chemical synthesis, fuel oil synthesis, metallurgical reducing gas, combined cycle power generation, fuel cells, hydrogen production and coal liquefaction. As an important equipment in the coal gasification process, the pulverized coal gasifier mixes coal powder with oxygen and water vapor and performs incomplete combustion at high temperature to generate synthesis gas. This process can not only improve the utilization efficiency of coal, but also reduce environmental pollution, and has important economic and environmental value. As an important tool, the simulation technology of the pulverized coal gasifier helps engineers and researchers better understand and optimize the coal gasification process. Numerical simulation can reveal the thermal flow field distribution characteristics of the pulverized coal gasifier, help improve the burner design, and improve the performance of the gasifier. The use of simulation technology can also more accurately characterize and analyze the temperature distribution in the pulverized coal gasifier, which is crucial to ensure gasification performance and process safety.

[0003] Traditional mechanism models tend to focus on the analysis of steady-state processes, and the research on the dynamic characteristics and transient processes of gasifiers is relatively insufficient. However, in actual operation, gasifiers often need to face various transient conditions and disturbances, so models that lack dynamics are difficult to meet actual needs.

[0004] In summary, a modeling method is needed that can improve the accuracy and calculation speed of the model to achieve high-precision simulation of the gasifier under all working conditions and in real time. Summary of the invention

[0005] The present invention provides a pulverized coal gasifier modeling method and device based on a CFD reduced-order model, so as to achieve high-precision simulation of the gasifier under all working conditions and in real time.

[0006] According to one aspect of the present invention, a gasifier modeling method based on a CFD reduced-order model is provided, comprising:

[0007] Constructing a flow network model of the gasifier based on the functional partitions of the gasifier, and constructing a chemical reaction model of each of the functional partitions;

[0008] Perform CFD simulation based on the flow network model and the chemical reaction model;

[0009] constructing a reduced-order model based on CFD simulation results and field experimental data of the gasifier;

[0010] A gasifier hybrid model is obtained by hybrid modeling of the reduced-order model and the mechanism model of the gasifier.

[0011] Optionally, the functional partitions include: a combustion zone, a jet expansion zone, a reflux mixing zone, a pipe flow zone and a quenching zone; accordingly, the flow network model of the gasifier is constructed based on the functional partitions of the gasifier, and the chemical reaction model of each of the functional partitions is constructed, including:

[0012] According to the positions and connection relationships of the combustion zone, the jet expansion zone, the reflux mixing zone, the tube flow zone and the quenching zone and the working principle of the gasifier, a flow network model of the gasifier is constructed;

[0013] The jet expansion zone model is constructed according to the momentum and energy transfer process of the jet;

[0014] A reflux mixing zone model is constructed based on the mixing characteristics of synthesis gas and unreacted coal powder;

[0015] The quenching zone model is constructed based on the heat and mass transfer model of the quenching ring and downcomer;

[0016] According to the chemical reactions generated by the functional partitions, chemical reaction formulas of the chemical reaction models are set.

[0017] Optionally, the performing CFD simulation based on the flow network model and the chemical reaction model includes:

[0018] Constructing a geometric model of the gasifier and meshing the geometric model;

[0019] A CFD model is constructed based on the flow network model, the chemical reaction model and the geometric model, and a CFD simulation is performed using the CFD model.

[0020] Optionally, the step of constructing a geometric model of the gasifier and meshing the geometric model includes:

[0021] According to the accurate positions of the various structures of the gasifier in the furnace, a three-dimensional structural model of the gasifier is established, and the three-dimensional structural model is simplified;

[0022] According to the internal structure of the gasifier and the fluid flow characteristics, a structured mixed unstructured grid method is used to perform grid division;

[0023] The mesh is encrypted at the burner of the mesh; the mesh independence check is performed based on the calculation results of different mesh densities.

[0024] Optionally, performing CFD simulation using the CFD model includes:

[0025] Setting boundary conditions according to the operating conditions of the gasifier, wherein the boundary conditions include inlet flow rate, temperature and pressure;

[0026] Set the sliding interface or overlapping grid between the moving area and the static area;

[0027] The Reynolds-averaged NS equations are closed by the Realizable k-ε model to simulate the closed interval of fluid calculation;

[0028] With pulverized coal as the discrete phase and gas as the continuous phase, the random orbit model under Lagrangian coordinates is used to track the movement of particles to simulate the heating of pulverized coal in the gasifier, and the gasification reaction of volatile matter and coke and the gas phase reaction between volatile matter and gasifying agent occur in sequence;

[0029] The interphase mass transfer was handled by the Lee model to simulate the interaction between the discrete phase and the continuous phase to obtain at least one CFD simulation result under different operating conditions.

[0030] Optionally, the building of a reduced-order model based on CFD simulation results and field experimental data of the gasifier includes:

[0031] Performing simulation calculation on at least one standard working condition of the gasifier in actual operation to obtain a working condition database;

[0032] Through the DOE test, the working conditions and parameters of the gasifier are designed based on the working condition database to obtain a reduced-order model parameter association sample table, wherein the parameter association sample table represents whether there is interaction when different variables are combined under different parameters and the degree of interaction;

[0033] The integrated gasifier finite element simulation model calls the CFD model for calculation according to the parameter association sample table to obtain a reduced-order model input parameter-output result sample table;

[0034] Classifying, merging and statistically analyzing the field experimental data to obtain a reduced-order model input parameter-equipment operating performance data table;

[0035] Performing a training data analysis of the reduced-order model by parameter dimension reduction to obtain a data analysis result, wherein the data analysis result represents the importance of each variable in the training data of the reduced-order model in affecting the performance;

[0036] Based on the reduced-order model parameter association sample table, the reduced-order model input parameter-output result sample table and the reduced-order model input parameter-equipment operation performance data table, proxy model building is performed, and the reduced-order model is obtained through the proxy model.

[0037] Optionally, the training data analysis of the reduced-order model by parameter dimension reduction includes:

[0038] Analyzing the field experimental data by principal component analysis to determine parameters as input variables of the reduced-order model;

[0039] The importance of each variable's impact on performance is determined and ranked by a sensitivity analysis method to obtain the data analysis result.

[0040] Optionally, obtaining the reduced-order model through a proxy model includes:

[0041] The result data according to different input working conditions are divided into static data and dynamic data, wherein the static data represents the data acquired at a specific time point or under stable working conditions, and the dynamic data represents the data that changes continuously with time or space;

[0042] A static reduced-order model and a dynamic reduced-order model are established according to the static data and the dynamic data respectively, and the static reduced-order model and the dynamic reduced-order model are verified and trained to obtain a reduced-order model that meets the analysis requirements.

[0043] Optionally, the method further includes: performing error evaluation on the prediction results of the proxy model based on the training samples, calculating the average error or the cross-validation CV value according to the evaluation results, and evaluating the stability and generalization ability of the reduced-order model through the average error or the CV value;

[0044] Optionally, the prediction accuracy of the proxy model is compared with the test data results to calculate the relative error value of the performance prediction results.

[0045] According to another aspect of the present invention, a gasifier modeling device based on a CFD reduced-order model is provided, comprising:

[0046] A first construction unit is used to construct a flow network model of the gasifier based on the functional partitions of the gasifier, and to construct a chemical reaction model of each of the functional partitions;

[0047] A simulation unit, used for performing CFD simulation based on the flow network model and the chemical reaction model;

[0048] A second construction unit is used to construct a reduced-order model based on CFD simulation results and field experimental data of the gasifier;

[0049] A modeling unit is used to obtain a gasifier hybrid model by hybrid modeling of the reduced-order model and the mechanism model of the gasifier.

[0050] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0051] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the gasifier modeling method based on the CFD reduced-order model described in any embodiment of the present invention.

[0052] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the gasifier modeling method based on the CFD reduced-order model described in any embodiment of the present invention when executed.

[0053] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program, which, when executed by a processor, implements the gasifier modeling method based on the CFD reduced-order model described in any embodiment of the present invention.

[0054] The technical solution of the embodiment of the present invention proposes the use of multidisciplinary and multi-dimensional coupling technology for the simulation of industrial pulverized coal gasifiers, and realizes a high-precision model by combining mechanism modeling with CFD reduced-order model data correction. It overcomes the shortcomings of poor externality caused by the lack of equipment structure data and insufficient mechanism data of traditional simple mechanism models or data models, and realizes high-precision simulation of the process.

[0055] 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

[0056] 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.

[0057] Figure 1 is a flow chart of a gasifier modeling method based on a CFD reduced-order model provided in Example 1 of the present invention;

[0058] Figure 2 is a flow chart of a method for constructing a flow network model and a chemical reaction model provided in the second embodiment of the present invention;

[0059] Figure 3 This is a schematic diagram of a gasification furnace partition structure applicable to the second embodiment of the present invention;

[0060] Figure 4 is a schematic diagram of a gasifier flow network model applicable to the second embodiment of the present invention;

[0061] Figure 5 is a flow chart of a CFD simulation method provided in Embodiment 3 of the present invention;

[0062] Figure 6 is a schematic diagram of a grid division applicable to the third embodiment of the present invention;

[0063] Figure 7 This is a schematic diagram of the jet velocity and turbulence intensity distribution results in a gasifier applicable to the third embodiment of the present invention;

[0064] Figure 8 is a flow chart of a reduced-order model construction method provided by Embodiment 4 of the present invention;

[0065] Fig. 9 is a structural schematic diagram of a gasifier modeling device based on a CFD reduced-order model provided in Embodiment 5 of the present invention;

[0066] Fig.10 It is a structural schematic diagram of an electronic device for implementing the gasifier modeling method based on a CFD reduced-order model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] 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.

[0068] 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.

[0069] Embodiment 1

[0070] Figure 1 This is a flow chart of a gasifier modeling method based on a CFD reduced-order model provided in the first embodiment of the present invention. This embodiment is applicable to the case of simulating an industrial pulverized coal gasifier. The method can be executed by a gasifier modeling device based on a CFD reduced-order model. The gasifier modeling device based on a CFD reduced-order model can be implemented in the form of hardware and / or software. The gasifier modeling device based on a CFD reduced-order model can be configured in an electronic device. Figure 1 As shown, the method includes:

[0071] S110. Construct a flow network model of the gasifier based on the functional partitions of the gasifier, and construct a chemical reaction model of each functional partition.

[0072] The flow network model is a mathematical model used to describe and analyze the flow of fluid in a pulverized coal gasifier. It abstracts and simplifies the structure of the system, the flow characteristics of different regions, and the connection relationship between the regions, and presents the flow path, flow distribution, and flow state in each region in an intuitive network form. For complex equipment such as pulverized coal gasifiers, its overall geometric structure must be analyzed in detail first. The shape, size, and relative position of each component in the entire device must be clarified. The flow network model includes nodes and connecting edges. In the flow network model, nodes are usually used to represent areas or locations with specific functions or specific flow states in the gasifier. For example, each divided functional partition can be regarded as a node. In addition, some key location points, such as inlets, outlets, and connection points between different regions, can also be set as nodes. Connecting edges are used to connect various nodes, which represent the flow path of the fluid between different regions or between different positions. Connecting edges can be marked with directions to indicate the flow direction of the fluid.

[0073] The chemical reaction model is a mathematical model used to describe and predict the chemical reaction process in the pulverized coal gasifier. The core of the chemical reaction model is a series of specific reaction equations, which clearly list the reactants, products and the stoichiometric relationship between them. In the chemical reaction model of the pulverized coal gasifier, there will be multiple reaction equations to describe the reaction process in different stages and different areas.

[0074] S120. Perform CFD simulation based on flow network model and chemical reaction model.

[0075] CFD (Computational Fluid Dynamics) simulation, that is, computational fluid dynamics simulation, is a technical means that uses computer numerical calculation methods to simulate fluid flow, heat transfer, mass transfer and related physical and chemical processes.

[0076] CFD simulation is closely related to chemical reaction models. Chemical reaction models describe the specific chemical reactions occurring in various areas of the gasifier, which determine the transformation of substances and changes in energy. CFD simulation obtains detailed information on physical and chemical processes such as fluid flow, heat transfer, and mass transfer in the gasifier through numerical calculations, and provides environmental parameters (such as temperature, pressure, flow rate, component concentration, etc.) for the chemical reaction model. These parameters are important factors affecting the reaction rate in the chemical reaction model. For example, an increase in temperature usually speeds up the rate of a chemical reaction, while a change in pressure affects the equilibrium constant and reaction direction of the reaction. At the same time, energy changes such as reaction heat in the chemical reaction model will also affect the energy equation in the CFD simulation, providing energy source terms and sink terms for the CFD simulation, thereby affecting the results of the entire CFD simulation.

[0077] CFD simulation can provide the flow network model with more accurate fluid flow parameters (such as flow rate, time, temperature, etc.) and physical and chemical process information in each area, which can be used to improve the construction of the flow network model and refine its description; and the flow network model can provide a macro fluid flow framework for CFD simulation, helping CFD simulation to determine the geometry and boundary conditions of the calculation domain.

[0078] S130. Construct a reduced-order model based on the CFD simulation results and field experimental data of the gasifier.

[0079] The complete physical model of the pulverized coal gasifier (such as a CFD-based model) is often very complex, involving a large number of variables, equations, and complex physical and chemical processes. Calculation and analysis of such a full-order model usually requires a large amount of computing resources (such as high-performance computers, long computing time, etc.). One of the main purposes of the reduced-order model is to simplify the model structure and reduce the amount of calculation, so that the calculation can be completed in a shorter time on an ordinary computer, thereby improving the computing efficiency, so that the system can be simulated, analyzed, and optimized multiple times quickly. The construction of the reduced-order model can be achieved based on physical principles and data-driven. The simplification based on physical principles is to reasonably simplify or ignore some minor physical processes or variables in the full-order model based on physical principles and actual operating conditions. For example, in the model of the pulverized coal gasifier, if some chemical reactions have a relatively small impact on the production and quality of syngas, and their occurrence conditions are relatively special, these chemical reactions can be simplified in the reduced-order model. Similarly, some small resistance factors that have little effect on fluid flow can be ignored in the reduced-order model, thereby simplifying the fluid dynamics part of the model. Through this simplification based on physical principles, the complexity of the model can be reduced to a certain extent while retaining the main physical characteristics of the system.

[0080] S140. A gasifier hybrid model is obtained by hybrid modeling of a reduced-order model and a mechanism model of a gasifier.

[0081] The construction of a hybrid model is a modeling process that combines data-driven methods and physical mechanisms. First, the key equations and principles of the mechanism model are integrated into the reduced-order model to ensure that the model can reflect the actual physical process; second, the parameters in the reduced-order model are adjusted to ensure that its output is consistent with the prediction of the mechanism model to achieve model synchronization. Through weighting, superposition or nesting, the advantages of the reduced-order model and the mechanism model are combined to form a hybrid model; finally, the hybrid model is tested using an independent validation data set to evaluate its predictive accuracy and stability.

[0082] The computational principle of the hybrid model is to combine the data-driven reduced-order model with the physics-based mechanism model to achieve more efficient and accurate calculations, including:

[0083] Data-driven principle: The reduced-order model learns the relationship between input parameters and output responses by fitting a large amount of simulation data, thereby achieving rapid prediction of complex systems.

[0084] Physical Mechanism Principles: Mechanistic models are based on physical laws and process principles, providing a deep understanding of system behavior and ensuring the physical consistency of the model.

[0085] Model fusion principle: The hybrid model combines the advantages of two models to improve the calculation speed and prediction accuracy while maintaining the physical meaning.

[0086] Global and local fitting: The local accuracy of reduced-order models is combined with the global simulation capabilities of mechanistic models to handle complex problems with high-precision simulation requirements.

[0087] Iterative update: The hybrid model can be iteratively updated based on new data to adapt to system changes or improve the adaptability of the model.

[0088] Multi-scale modeling: Hybrid models can handle problems at different scales from micro to macro, and realize multi-scale modeling and analysis.

[0089] The construction and calculation principle of the hybrid model is a complex process that requires comprehensive consideration of multiple factors such as data quality, model complexity, prediction accuracy, and computational efficiency. Through continuous experimentation and optimization, an efficient hybrid model suitable for specific application scenarios can be developed.

[0090] The embodiment of the present invention proposes to adopt multidisciplinary and multi-dimensional coupling technology for the simulation of industrial pulverized coal gasifiers, with mechanism modeling as the main core, assisted by CFD reduced-order model data correction to achieve high-precision simulation of the gasifier. In this way, various physical property calculation models, reaction and heat transfer related calculation models of chemical process simulation are fully utilized, thereby reducing the requirements for process data samples, so that the model not only has good local approach performance, but also has good global generalization ability; and the high-precision model is realized by combining CFD reduced-order model data correction, which overcomes the shortcomings of poor extension caused by the lack of equipment structure data and insufficient mechanism data of traditional simple mechanism models or data models, and realizes high-precision simulation of the process.

[0091] Embodiment 2

[0092] Figure 2 This is a flow chart of a method for constructing a flow network model and a chemical reaction model provided by the second embodiment of the present invention. This embodiment further explains the above-mentioned first embodiment. Functional partitions include: combustion zone, jet expansion zone, reflux mixing zone, pipe flow zone and quenching zone. Figure 2 As shown, the method includes:

[0093] S210. Construct a flow network model of the gasifier according to the positions and connection relationships of the combustion zone, the jet expansion zone, the reflux mixing zone, the tube flow zone and the quenching zone and the working principle of the gasifier.

[0094] A detailed structural analysis of the gasifier is conducted to clarify the physical characteristics and functions of each partition. The gasifier is divided into a combustion zone, a jet expansion zone, a reflux mixing zone, a pipe flow zone, and a quenching zone according to the flow and mixing characteristics of the materials in the furnace. In the combustion zone, the combustion reaction of coal and oxygen mainly occurs, generating high temperature; in the jet expansion zone, the coal powder and oxygen are mixed and then injected into the gasifier at high speed to form a jet. In the reflux mixing zone, the synthesis gas is mixed with the incompletely reacted coal powder to form a reflux; in the pipe flow zone, the synthesis gas flows along the axis of the gasifier to transfer heat and mass; in the quenching zone, the synthesis gas is rapidly cooled through the quenching chamber to prepare for subsequent treatment. Figure 3 It is a schematic diagram of a gasification furnace partition structure applicable to the second embodiment of the present invention. Figure 4 It is a schematic diagram of a gasifier flow network model applicable to the second embodiment of the present invention.

[0095] S220. Construct a jet expansion zone model according to the momentum and energy transfer process of the jet and set the corresponding chemical reaction formula.

[0096] S230. Construct a reflux mixing zone model based on the mixing characteristics of the synthesis gas and the unreacted coal powder.

[0097] S240. Construct a quenching zone model based on the heat and mass transfer model of the quenching ring and the downcomer.

[0098] S250. According to the chemical reactions generated in each functional partition, a chemical reaction formula of each chemical reaction model is set.

[0099] The combustion zone model takes into account the kinetic and thermodynamic characteristics of the combustion reaction. The specific reactions occurring in the combustion zone are as follows:

[0100] ;

[0101] Jet expansion zone model, analyzing the momentum and energy transfer process of the jet:

[0102] ;

[0103] Reflux mixing zone model to study the mixing characteristics of syngas and unreacted coal powder:

[0104] ;

[0105] The pipe flow model simulates the flow and transfer process of the synthesis gas in the pipe:

[0106] ;

[0107] The quenching zone model is used to establish the heat and mass transfer model of the quenching ring and the downcomer. In the downcomer of the quenching chamber, the high-temperature synthesis gas and the quenching water undergo intense heat and mass transfer and a shift reaction occurs. The chemical reactions in the quenching chamber are as follows:

[0108] .

[0109] The chemical reaction model and the flow model influence and cooperate with each other. Chemical reactions produce or consume substances and energy, which will affect the flow characteristics of the fluid in the furnace, such as flow rate, flow direction, turbulence, etc. For example, the high-temperature gas produced by the combustion reaction expands the gas volume, changing the flow direction and flow rate of the fluid; the gasification reaction consumes the reactants and generates synthesis gas, which affects the composition and density of the fluid, thereby affecting the flow characteristics of the fluid. At the same time, the fluid flow process will also affect the rate and balance of the chemical reaction. By coupling the chemical reaction model with the flow model, the complex physical and chemical processes in the gasifier can be simulated more comprehensively and accurately, providing more reliable support for the research, design, optimization and operation control of the gasifier.

[0110] Embodiment 3

[0111] Figure 5 1 is a flow chart of a CFD simulation method provided by the third embodiment of the present invention. This embodiment further explains the first embodiment above. Figure 5 As shown, the method includes:

[0112] S510, constructing a geometric model of the gasifier and meshing the geometric model.

[0113] In the embodiment of the present invention, S510 specifically includes:

[0114] Establishing a three-dimensional structural model of the gasifier according to the positions of various structures of the gasifier in the furnace, and simplifying the three-dimensional structural model;

[0115] According to the internal structure of the gasifier and the fluid flow characteristics, a structured mixed unstructured grid method is used to perform grid division;

[0116] The mesh is encrypted at the burner of the mesh; the mesh independence check is performed based on the calculation results of different mesh densities.

[0117] Computational fluid dynamics (CFD) software is used to simulate the core unit under multiple conditions to obtain the flow and reaction characteristics under different operating conditions. According to the CFD simulation results, the model is reduced to reduce the amount of calculation and improve the applicability of the model. Specifically, it includes:

[0118] Geometric model construction: Analyze the design drawings of the pulverized coal gasifier, clarify the key features required for the three-dimensional structural model and the accurate position of each structure in the furnace, and ensure that the model accurately reflects the actual equipment structure. Use CAD software to build a three-dimensional structural model of the gasifier. Simplify the model as necessary and delete details that do not affect the flow field analysis to improve calculation efficiency.

[0119] Mesh division: According to the internal structure of the gasifier and the fluid flow characteristics, the mesh adopts the structured mixed unstructured mesh method, and is encrypted near the burner. The mesh independence check is performed based on the calculation results of different mesh densities. The accuracy and division method of mesh division have an important impact on the accuracy of the simulation results and the calculation efficiency. Based on previous experience, while ensuring the calculation accuracy, the mesh size is appropriately increased to reduce the amount of calculation. Figure 6 Schematic diagram of a grid division applicable to the third embodiment of the present invention. Figure 6 As shown in the figure, due to the large temperature gradient and velocity gradient near the burner, the mesh is refined to capture more detailed information inside the gasifier.

[0120] S520, constructing a CFD model based on the flow network model, the chemical reaction model, and the geometric model, and performing CFD simulation through the CFD model.

[0121] In the embodiment of the present invention, S520 specifically includes: setting boundary conditions according to the operating conditions of the gasifier, the boundary conditions including inlet flow rate, temperature and pressure;

[0122] Set the sliding interface or overlapping grid between the moving area and the static area;

[0123] The Reynolds-averaged NS equations are closed by the Realizable k-ε model to simulate the closed interval of fluid calculation;

[0124] With pulverized coal as the discrete phase and gas as the continuous phase, the random orbit model under Lagrangian coordinates is used to track the movement of particles to simulate the heating of pulverized coal in the gasifier, and the gasification reaction of volatile matter and coke and the gas phase reaction between volatile matter and gasifying agent occur in sequence;

[0125] The interphase mass transfer was handled by the Lee model to simulate the interaction between the discrete phase and the continuous phase to obtain at least one CFD simulation result under different operating conditions.

[0126] According to the actual operating conditions, set appropriate boundary conditions, such as inlet flow rate, temperature, pressure, etc., and set the sliding interface or overlapping grid between the moving area and the static area. The working temperature span of the gasifier is large, and the thermal properties of the working fluid, such as density, viscosity, specific heat capacity and thermal conductivity, all change with temperature. The physical properties used in the calculation include density (ρ), dynamic viscosity (μ), thermal conductivity (λ), and constant pressure specific volume (Cp). The flow section is the inlet boundary condition. By giving the flow rate, temperature, pressure, liquid level, turbulence intensity and other information at the inlet of each component, the changes of various physical quantities are transmitted to the calculation area. In the present invention, the calculation amount, accuracy and stability are comprehensively considered, and the Realizable k-ε model is used to close the NS equation after Reynolds averaging. Pulverized coal is used as a discrete phase and gas as a continuous phase. The random orbit model under Lagrangian coordinates is used to track the movement of particles, while considering the interaction between the discrete phase and the continuous phase. Pulverized coal is heated in the gasifier, and volatile matter and coke gasification reactions occur in turn, and gas phase reactions also occur between volatile matter and gasifying agent. The devolatilization reaction of coal powder can be expressed by a first-order reaction rate equation. The coke gasification reaction rate is controlled by chemical kinetics and diffusion. Highly turbulent flow and violent combustion and other gas phase reactions exist simultaneously in the gasifier. Turbulence causes the flame structure to twist and wrinkle. The changes in local temperature, concentration, velocity and physical properties caused by chemical reactions in turn affect the turbulent structure. The interaction and influence of turbulence and gas phase reactions are important processes in the gasifier. Therefore, reasonable simulation of turbulent gas phase reactions is the key to gasifier simulation. Since the EDC model can consider detailed chemical reaction mechanisms in turbulent flow, it is more suitable for revealing the complex turbulent reaction coupling process near the burner of the gasifier. Therefore, the embodiment of the present invention uses the EDC model containing elementary reactions to simulate and calculate the turbulent gas phase reactions in the gasifier. Figure 7This is a schematic diagram of the jet velocity and turbulence intensity distribution results in a gasifier applicable to the third embodiment of the present invention. The calculation results show that all oxidants and fuels enter the furnace through a single burner, the momentum of the central jet is large, the jet distance is far, and a large-scale reflux will be formed around the central jet. This feature is consistent with the flow field distribution of a top-mounted, bottom-spraying single-burner gasifier. Under the condition of a single burner, the outlet temperature is higher, and the particles refluxed to the burner mouth are melted and attached to the outlet end face under the action of a large scale. Therefore, the circulating cooling water of the burner itself acts to rapidly cool the molten ash to form coke.

[0127] Embodiment 4

[0128] Figure 8 4 is a flowchart of a method for constructing a reduced-order model provided by the fourth embodiment of the present invention. This embodiment further explains the above-mentioned first embodiment. Figure 8 As shown, the method includes:

[0129] S810, performing simulation calculation on at least one operating condition of the gasifier to obtain an operating condition database.

[0130] S820. Through DOE experiments, the operating conditions and parameters of the gasifier are designed based on the operating condition database to obtain a reduced-order model parameter association sample table. The parameter association sample table represents whether there is interaction when different variables are combined under different parameters and the degree of interaction.

[0131] S830, the integrated gasifier finite element simulation model calls the CFD model for calculation according to the parameter association sample table to obtain a reduced-order model input parameter-output result sample table.

[0132] S840. Classify, merge and statistically analyze the field experimental data to obtain the reduced-order model input parameter-equipment operation performance data table.

[0133] S850, analyzing the training data of the reduced-order model by parameter dimension reduction to obtain a data analysis result, wherein the data analysis result represents the importance of each variable in the training data of the reduced-order model in affecting the performance.

[0134] In the embodiment of the present invention, S850 specifically includes:

[0135] Analyzing the field experimental data by principal component analysis to determine parameters as input variables of the reduced-order model;

[0136] The importance of each variable's impact on performance is determined and ranked by a sensitivity analysis method to obtain the data analysis result.

[0137] PCA (Principal Component Analysis), or principal component analysis, is used for the physical test data of the gasifier. A set of variables that may be correlated is converted into a set of linearly uncorrelated variables through orthogonal transformation to reduce the complexity of the analysis problem. The key parameters that have a greater impact on the performance results of the gasifier are found to provide a certain decision-making basis for sorting out which parameters to use as input variables of the proxy model. In order to help find the key parameters that have a greater impact on the output response of the gasifier, the sensitivity analysis method is used to analyze the importance of the equipment research variables to the equipment output performance results, and the parameters are ranked according to their importance in affecting the performance.

[0138] S860, based on the reduced-order model parameter association sample table, the reduced-order model input parameter-output result sample table and the reduced-order model input parameter-equipment operation performance data table, a proxy model is built, and a reduced-order model is obtained through the proxy model.

[0139] During the forward modeling process, commercially mature finite element software will be used to simulate and calculate various operating conditions of the gasifier, thereby forming an operating condition database that is not available in normal production.

[0140] Before reverse modeling, DOE experimental design technology was used to conduct multi-condition and multi-parameter design of the gasifier to form a parameter correlation sample table.

[0141] The finite element simulation model of the integrated gasifier is repeatedly called to perform calculations based on the sample table of the DOE experimental design to generate a sample table of the input parameters and output results of the gasifier reduced-order simulation model.

[0142] Collect and analyze existing physical test data of gasifier operation;

[0143] Classify, merge and statistically analyze the data, such as the maximum, minimum, mean and variance of equipment research variables and performance output response, percentile statistics, and preliminarily analyze the integrity and rationality of centrifuge equipment operation data;

[0144] Form the input parameters for the operation of the gasifier equipment - a data table of equipment operating performance.

[0145] In the embodiment of the present invention, S860 specifically includes:

[0146] According to the different input conditions, the result data is divided into static data and dynamic data. Static data represents the data obtained at a specific time point or under stable conditions, and dynamic data represents the data that changes continuously with time or space.

[0147] A static reduced-order model and a dynamic reduced-order model are established according to the static data and the dynamic data respectively, and the static reduced-order model and the dynamic reduced-order model are verified and trained to obtain a reduced-order model that meets the analysis requirements.

[0148] The collected gasifier operation test data and simulation sample data are used to perform surrogate model modeling using the surrogate model modeling method, and a mathematical model that can reflect the input-output relationship of the gasifier is constructed.

[0149] Since the result data of different input conditions are divided into static data and dynamic data, static reduced order models and dynamic reduced order models are established according to the static data and dynamic data, and the static reduced order models and dynamic reduced order models are verified and trained to obtain reduced order models that meet the analysis requirements, and output FMU or ROM format as needed.

[0150] In order to establish a gasifier reduced-order model with high enough accuracy, on the one hand, it is necessary to ensure that the sample data used for fitting is sufficient and evenly distributed in the design space. At least 10 groups of samples are required for one parameter, and the number of samples corresponding to n parameters is at least n*10. On the other hand, for given sample data, using a suitable proxy model to describe the input-output relationship of the sedimentation centrifuge equipment can also help improve the accuracy of the established proxy model.

[0151] Preferably, the response surface model and the Kriging model are used in the present invention to process the gasifier reaction part and the quenching chamber part respectively. The construction of the proxy model mainly includes two aspects: 1. Using a certain method to select sample points for constructing the model, and the selection method is related to the sampling strategy of the proxy model; 2. Fitting data to establish a model. The basic idea is to select a batch of sample points in the design space by experimental means, obtain the dynamic response of the sample points through experiments or numerical analysis, and establish a proxy model that can characterize the dynamic response of the structure by fitting the data. Using a proxy model instead of the original complex structural model for dynamic analysis and optimization design can reduce the amount of calculation.

[0152] If the data presents a certain linear or nonlinear relationship and you want to build a reduced-order model with better interpretability, you can consider using a response surface model. It builds a mathematical model in the form of a polynomial function based on the experimental data or simulation data between the input variables and the output variables of the system to approximate the input-output relationship of the system. For example, with the raw coal characteristics and operating conditions as input variables and the synthesis gas output and quality as output variables, a response surface model is built by fitting the data as a reduced-order model to quickly predict the output results of the system.

[0153] The Kriging model is also a commonly used data-driven order reduction model method. It predicts the data of unknown points by establishing the covariance function between sample data based on the spatial correlation of data. The Kriging model has better performance when processing data with local correlation. For example, in the simulation data of certain local areas of the pulverized coal gasifier, if there is obvious local correlation, the Kriging model can be used for order reduction.

[0154] In the fourth embodiment of the present invention, the method may further include the following steps:

[0155] Performing error evaluation on the prediction results of the proxy model based on the training samples, calculating the average error or the cross-validation CV value according to the evaluation results, and evaluating the stability and generalization ability of the reduced-order model through the average error or the CV value;

[0156] The prediction accuracy of the proxy model is compared with the test data results, and the relative error value of the performance prediction results is calculated.

[0157] In order to ensure the predictive ability of the gasifier reduced-order model, the accuracy of the surrogate model needs to be verified after the surrogate model is built. The leave-one-out method is used for internal accuracy inspection, the error between the prediction results of the surrogate model and the training samples is evaluated, and the cross validation CV (Cross Validation) value is calculated.

[0158] Using the new gasifier operation physical test data, the accuracy of the proxy model is externally checked. That is, the prediction accuracy of the proxy model is compared with the new test data results, and the relative error value of the performance prediction results is calculated.

[0159] For proxy models whose accuracy does not meet the application requirements, you can supplement the training sample data or choose other proxy model modeling algorithms to retrain the proxy model.

[0160] After the reduced-order model is verified, the FMU intermediate format mathematical model is exported. The model has clear inputs and outputs, can run independently, and perform fast simulation calculations. The exported FMU model can run independently and does not rely on the modeling environment of any proxy model. The FMU model is integrated into the pulverized coal gasification mechanism process mechanism model system for system simulation to complete more complex system simulations.

[0161] The embodiment of the present invention proposes to adopt multidisciplinary and multi-dimensional coupling technology for the simulation of industrial pulverized coal gasifiers, with mechanism modeling as the main core, assisted by CFD reduced-order model data correction to achieve high-precision simulation of the gasifier. In this way, various physical property calculation models, reaction and heat transfer related calculation models of chemical process simulation are fully utilized, thereby reducing the requirements for process data samples, so that the model not only has good local approach performance, but also has good global generalization ability; and the high-precision model is achieved by combining CFD reduced-order model data correction, overcoming the shortcomings of poor extension caused by the lack of equipment structure data and insufficient mechanism data of traditional simple mechanism models or data models, and achieving high-precision simulation of the process.

[0162] Embodiment 5

[0163] Fig. 9 Schematic diagram of the structure of a gasifier modeling device based on a CFD reduced-order model provided in Embodiment 5 of the present invention. Fig. 9 As shown, the device comprises:

[0164] A first construction unit 910 is used to construct a flow network model of the gasifier based on the functional partitions of the gasifier, and to construct a chemical reaction model of each functional partition;

[0165] A simulation unit 920, for performing CFD simulation based on a flow network model and a chemical reaction model;

[0166] A second construction unit 930 is used to construct a reduced-order model based on the CFD simulation results and the field experimental data of the gasifier;

[0167] The modeling unit 940 is used to obtain a gasifier hybrid model by hybrid modeling of the reduced-order model and the mechanism model of the gasifier.

[0168] The gasifier modeling device based on the CFD reduced-order model provided in the embodiment of the present invention can execute the gasifier modeling method based on the CFD reduced-order model provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0169] Embodiment 6

[0170] Fig.10A 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.

[0171] like Fig.10 As 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. The input / output (I / O) interface 15 is also connected to the bus 14.

[0172] 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.

[0173] 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 special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the gasifier modeling method based on the CFD reduced-order model.

[0174] In some embodiments, the gasifier modeling method based on the CFD reduced-order 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 gasifier modeling method based on the CFD reduced-order model described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the gasifier modeling method based on the CFD reduced-order model in any other appropriate manner (e.g., by means of firmware).

[0175] 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.

[0176] 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.

[0177] 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 conjunction 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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 gasifier modeling method based on CFD reduced-order model, characterized in that: include: Constructing a flow network model of the gasifier based on the functional partitions of the gasifier, and constructing a chemical reaction model of each of the functional partitions; Perform CFD simulation based on the flow network model and the chemical reaction model; constructing a reduced-order model based on CFD simulation results and field experimental data of the gasifier; A gasifier hybrid model is obtained by hybrid modeling of the reduced-order model and the mechanism model of the gasifier.

2. The method according to claim 1, characterized in that The functional partitions include: a combustion zone, a jet expansion zone, a reflux mixing zone, a pipe flow zone and a quenching zone; accordingly, the flow network model of the gasifier is constructed based on the functional partitions of the gasifier, and the chemical reaction model of each of the functional partitions is constructed, including: According to the positions and connection relationships of the combustion zone, the jet expansion zone, the reflux mixing zone, the tube flow zone and the quenching zone and the working principle of the gasifier, a flow network model of the gasifier is constructed; The jet expansion zone model is constructed according to the momentum and energy transfer process of the jet; A reflux mixing zone model is constructed based on the mixing characteristics of synthesis gas and unreacted coal powder; The quenching zone model is constructed based on the heat and mass transfer model of the quenching ring and downcomer; According to the chemical reactions generated by the functional partitions, chemical reaction formulas of the chemical reaction models are set.

3. The method according to claim 1, characterized in that The CFD simulation based on the flow network model and the chemical reaction model includes: Constructing a geometric model of the gasifier and meshing the geometric model; A CFD model is constructed based on the flow network model, the chemical reaction model and the geometric model, and a CFD simulation is performed using the CFD model.

4. The method according to claim 3, characterized in that The step of constructing a geometric model of the gasifier and meshing the geometric model includes: Establishing a three-dimensional structural model of the gasifier according to the positions of various structures of the gasifier in the furnace, and simplifying the three-dimensional structural model; According to the internal structure of the gasifier and the fluid flow characteristics, a structured mixed unstructured grid method is used to perform grid division; The mesh is encrypted at the burner of the mesh; the mesh independence check is performed based on the calculation results of different mesh densities.

5. The method according to claim 3, characterized in that: The performing CFD simulation by using the CFD model comprises: Setting boundary conditions according to the operating conditions of the gasifier, wherein the boundary conditions include inlet flow rate, temperature and pressure; Set the sliding interface or overlapping grid between the moving area and the static area; The Reynolds-averaged NS equations are closed by the Realizable k-ε model to simulate the closed interval of fluid calculation; With pulverized coal as the discrete phase and gas as the continuous phase, the random orbit model under Lagrangian coordinates is used to track the movement of particles to simulate the heating of pulverized coal in the gasifier, and the gasification reaction of volatile matter and coke and the gas phase reaction between volatile matter and gasifying agent occur in sequence; The interphase mass transfer was handled by the Lee model to simulate the interaction between the discrete phase and the continuous phase to obtain at least one CFD simulation result under different operating conditions.

6. The method according to claim 5, characterized in that The reduced-order model is constructed based on the CFD simulation results and the field experimental data of the gasifier, including: Performing simulation calculation on at least one standard working condition of the gasifier in actual operation to obtain a working condition database; Through the DOE test, the working conditions and parameters of the gasifier are designed based on the working condition database to obtain a reduced-order model parameter association sample table, wherein the parameter association sample table represents whether there is interaction when different variables are combined under different parameters and the degree of interaction; The integrated gasifier finite element simulation model calls the CFD model for calculation according to the parameter association sample table to obtain a reduced-order model input parameter-output result sample table; Classifying, merging and statistically analyzing the field experimental data to obtain a reduced-order model input parameter-equipment operating performance data table; Performing a training data analysis of the reduced-order model by parameter dimension reduction to obtain a data analysis result, wherein the data analysis result represents the importance of each variable in the training data of the reduced-order model in affecting the performance; Based on the reduced-order model parameter association sample table, the reduced-order model input parameter-output result sample table and the reduced-order model input parameter-equipment operation performance data table, proxy model building is performed, and the reduced-order model is obtained through the proxy model.

7. The method according to claim 6, characterized in that The training data analysis of the reduced-order model by parameter dimension reduction includes: Analyzing the field experimental data by principal component analysis to determine parameters as input variables of the reduced-order model; The importance of each variable's impact on performance is determined and ranked by a sensitivity analysis method to obtain the data analysis result.

8. The method according to claim 6, characterized in that The step of obtaining the reduced-order model through a proxy model includes: The result data according to different input working conditions are divided into static data and dynamic data, wherein the static data represents the data acquired at a specific time point or under stable working conditions, and the dynamic data represents the data that changes continuously with time or space; A static reduced-order model and a dynamic reduced-order model are established according to the static data and the dynamic data respectively, and the static reduced-order model and the dynamic reduced-order model are verified and trained to obtain a reduced-order model that meets the analysis requirements.

9. The method according to claim 8, characterized in that Also includes: Performing error evaluation on the prediction results of the proxy model based on the training samples, calculating the average error or the cross-validation CV value according to the evaluation results, and evaluating the stability and generalization ability of the reduced-order model through the average error or the CV value; and / or, The prediction accuracy of the proxy model is compared with the test data results, and the relative error value of the performance prediction results is calculated.

10. A gasifier modeling device based on a CFD reduced-order model, characterized in that: include: A first construction unit is used to construct a flow network model of the gasifier based on the functional partitions of the gasifier, and to construct a chemical reaction model of each of the functional partitions; A simulation unit, used for performing CFD simulation based on the flow network model and the chemical reaction model; A second construction unit is used to construct a reduced-order model based on CFD simulation results and field experimental data of the gasifier; A modeling unit is used to obtain a gasifier hybrid model by hybrid modeling of the reduced-order model and the mechanism model of the gasifier.

11. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the gasifier modeling method based on the CFD reduced-order model as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the gasifier modeling method based on a CFD reduced-order model according to any one of claims 1 to 9 when executed.

13. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the gasifier modeling method based on a CFD reduced-order model according to any one of claims 1 to 9.

Images