Model training method for predicting one-dimensional combustion characteristics of porous medium combustor

Abstract

The invention provides a model training method for predicting one-dimensional combustion characteristics of a porous medium combustor, and the method comprises the steps: carrying out the modeling of a combustion process of the porous medium combustor, and obtaining a combustion model; numerical simulation is conducted based on the combustion model, and temperature field one-dimensional distribution of the porous medium combustor at each first sampling point in the spatial distribution range of the working condition parameter variables is obtained; a target interpolation mode is adopted, temperature field one-dimensional distribution of the porous medium combustor at each second sampling point is obtained, and the temperature field one-dimensional distribution conforms to the change rule along with working condition parameter variables; and taking the one-dimensional distribution of the temperature field of the porous medium combustor at each sampling point as a training set, and training the neural network model to obtain a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium combustor. Therefore, the target physical law can be better approached, the situation of deviating from the physical law under the condition of small sample quantity is avoided, and more accurate prediction precision is realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of gas turbines, and in particular to a model training method for predicting one-dimensional combustion characteristics of a porous medium burner. Background Art

[0002] At present, the main application areas of porous media combustion technology are concentrated in normal pressure, low temperature and low flow rate environments. In contrast, the working environment of the gas turbine combustion chamber is characterized by high pressure, high temperature and high speed. Due to this difference in environment, the application of porous media combustion technology to gas turbines faces a series of challenges, such as achieving flame stability under high pressure environment, resisting the ablation of high temperature flame on the burner material, and facing high-frequency thermal shock.

[0003] In order to meet the rapid iteration requirements of gas turbine burner structure design and realize the application of porous media combustion technology in this field, the first task is to numerically simulate the burner structure designed by prior analysis to predict the combustion characteristics of the burner. Then, iterative optimization technology is used to adjust the equivalence ratio and flow rate boundaries of stable combustion based on the numerical simulation results to achieve multivariate regulation of variable heat load and work power over a wide range. This process provides the best design solution for subsequent test piece preparation and burner performance testing.

[0004] Related technologies can predict the combustion characteristics of burners through neural network models. However, neural network models usually require a large amount of training data to effectively learn patterns and laws, especially when dealing with complex problems or high-dimensional data. For small sample points, due to insufficient data, the neural network model may overfit or fail to capture the real physical laws well, thus affecting the prediction accuracy of the combustion characteristics of the burner. Summary of the invention

[0005] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0006] To this end, the present disclosure proposes a model training method for predicting the one-dimensional combustion characteristics of a porous medium burner, a prediction method, device, electronic device, computer-readable storage medium and computer program product for the one-dimensional combustion characteristics of a porous medium burner, so as to solve the problem in the related technology that for small sample points, due to insufficient data volume, the neural network model may overfit or fail to capture the real physical laws well, thereby affecting the prediction accuracy of the combustion characteristics of the burner.

[0007] The first aspect of the present disclosure proposes a model training method for predicting the one-dimensional combustion characteristics of a porous medium burner, comprising: modeling the combustion process of a porous medium burner of a target structure to obtain a combustion model, and determining operating parameter variables and the spatial distribution range of the operating parameter variables; for multiple first sampling points in the spatial distribution range, performing numerical simulation based on the combustion model to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner; for multiple second sampling points in the spatial distribution range, performing numerical simulation based on the combustion model to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points. point, adopting the target interpolation method, based on the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, obtain the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points conforms to the target physical law, and the target physical law is the law of change of the one-dimensional distribution of the temperature field with the operating condition parameter variable; the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points and each of the second sampling points is used as a training set to train the neural network model, and obtain a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

[0008] The second aspect embodiment of the present disclosure proposes a method for predicting the one-dimensional combustion characteristics of a porous medium burner, comprising: obtaining a target prediction model, wherein the target prediction model is trained based on the method described in the first aspect embodiment; using the target prediction model to predict the one-dimensional combustion characteristics of the porous medium burner, and obtaining a one-dimensional distribution of the temperature field of the porous medium burner at a target value of an operating parameter variable, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner; based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, determining the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value point.

[0009] The third aspect of the present disclosure proposes a model training device for predicting the one-dimensional combustion characteristics of a porous medium burner, including: a modeling module, which is used to model the combustion process of a porous medium burner of a target structure, obtain a combustion model, and determine operating parameter variables and the spatial distribution range of the operating parameter variables; a simulation module, which is used to perform numerical simulation based on the combustion model for multiple first sampling points in the spatial distribution range, and obtain the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner; an acquisition module, which is used to perform numerical simulation for multiple first sampling points in the spatial distribution range based on the combustion model, and obtain the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points. A plurality of second sampling points, adopting a target interpolation method, based on the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, obtains the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points conforms to the target physical law, and the target physical law is the law of change of the one-dimensional distribution of the temperature field with the operating condition parameter variable; a training module, used to use the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points and each of the second sampling points as a training set, train the neural network model, and obtain a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

[0010] The fourth aspect embodiment of the present disclosure proposes a prediction device for one-dimensional combustion characteristics of a porous medium burner, comprising: an acquisition module, used to acquire a target prediction model, wherein the target prediction model is trained based on the method described in the first aspect embodiment; a prediction module, used to use the target prediction model to predict the one-dimensional combustion characteristics of the porous medium burner, and obtain a one-dimensional distribution of the temperature field of the porous medium burner at a target value of an operating parameter variable, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner; a temperature determination module, used to determine the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value of the operating parameter variable based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable.

[0011] The electronic device proposed in the fifth aspect embodiment of the present disclosure includes: a processor, and a memory connected to the processor in communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner as proposed in the first aspect embodiment of the present disclosure, or to implement the prediction method of the one-dimensional combustion characteristics of a porous medium burner as proposed in the second aspect embodiment of the present disclosure.

[0012] The sixth aspect embodiment of the present disclosure proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner as proposed in the first aspect embodiment of the present disclosure, or to implement the prediction method of the one-dimensional combustion characteristics of a porous medium burner as proposed in the second aspect embodiment of the present disclosure.

[0013] The seventh aspect embodiment of the present disclosure proposes a computer program product, including a computer program, which, when executed by a processor, implements the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner as proposed in the first aspect embodiment of the present disclosure, or implements the prediction method of the one-dimensional combustion characteristics of a porous medium burner as proposed in the second aspect embodiment of the present disclosure.

[0014] The technical solution proposed in the present disclosure models the combustion process of a porous medium burner of a target structure to obtain a combustion model, performs numerical simulation based on the combustion model, and obtains a one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, thereby achieving high-fidelity numerical simulation to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, and by adopting a target interpolation method, based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, obtains the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point, which can effectively expand the number of sampling points, thereby expanding the number of training samples in the training set, and improving the generalization ability of the target prediction model. The one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point conforms to the target physical law, and realizes the coupling of physical information on the basis of high-fidelity numerical simulation, so that the target prediction model obtained by training the neural network model based on the training set can better approximate the target physical law when predicting the one-dimensional combustion characteristics of the porous medium burner, avoid the deviation from the physical law under the condition of a small sample number, and achieve more accurate prediction accuracy. By adopting the target prediction model, the one-dimensional combustion characteristics of the porous medium burner are predicted, and the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable is obtained, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner. Based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value are determined, so that the one-dimensional combustion characteristics of the porous medium burner can be quickly predicted based on the target prediction model, and the target physical laws can be better approached during the prediction, avoiding the deviation from the physical laws under the condition of small sample quantity, and achieving more accurate prediction accuracy.

[0015] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A schematic flow chart of a model training method for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure;

[0018] Figure 2 A schematic diagram of the structure and initial structural parameters of a porous medium burner provided in an embodiment of the present disclosure;

[0019] Figure 3 A schematic flow chart of a method for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure;

[0020] Figure 4 is a distribution diagram of the first candidate sampling point, the second candidate sampling point, and the second sampling point in the spatial distribution range of the operating condition parameter variable;

[0021] Figure 5 It is a schematic diagram of the temperature response surface obtained based on physical information;

[0022] Figure 6 It is a schematic diagram of the structure of the deep neural network model;

[0023] Figure 7 A schematic diagram of the average temperature, maximum temperature and outlet temperature of a porous medium burner at multiple values ​​of operating parameter variables;

[0024] Figure 8 Another schematic diagram of the average temperature, maximum temperature and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variable;

[0025] Fig. 9 Another schematic diagram of the average temperature, maximum temperature and outlet temperature of a porous medium burner at multiple values ​​of operating parameter variables;

[0026] Fig.10 Another schematic diagram of the average temperature, maximum temperature and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variable;

[0027] Fig.11It is a cloud diagram showing the actual changes of the average temperature, maximum temperature and outlet temperature of the porous medium burner with the inlet air flow rate and the equivalent ratio within the range of 0.3-20m / s and equivalence ratio of 0.4-0.8;

[0028] Fig.12 A schematic diagram of the structure of a model training device for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure;

[0029] Fig.13 A schematic diagram of the structure of a device for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure;

[0030] Fig.14 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0031] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0032] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0033] In order to meet the rapid iteration requirements of gas turbine burner structure design and realize the application of porous media combustion technology in this field, the first task is to numerically simulate the burner structure designed by prior analysis to predict the combustion characteristics of the burner. Then, iterative optimization technology is used to adjust the equivalence ratio and flow rate boundaries of stable combustion based on the numerical simulation results to achieve multivariate regulation of variable heat load and work power over a wide range. This process provides the best design solution for subsequent test piece preparation and burner performance testing.

[0034] For porous media combustion technology research, the use of high-fidelity numerical simulations usually requires a lot of computing time and resources. This is because porous media combustion problems involve multiple coupled physical and chemical phenomena such as heat, mass transfer, chemical reactions, and momentum transfer. In addition, in order to accurately describe the chemical reactions during the combustion process, detailed chemical mechanisms are required, which may include hundreds of chemical species and thousands of reactions. Solving the rate equations of these chemical reactions requires a lot of calculations. In design optimization problems (under multi-parameter query scenarios), a large amount of design space needs to be explored for parameter optimization, sensitivity analysis, or uncertainty quantification to find the optimal solution. It may be impractical to use high-fidelity numerical simulations to evaluate each design point.

[0035] Parameterized surrogate models can significantly reduce computational costs and time, but their prediction accuracy needs to be improved, and they may deviate from the physical laws dominated by the control equations and lack physical interpretability. On the other hand, it is very important to easily embed parameterized surrogate models into existing engineering design software, which requires consideration of factors such as software architecture, interface design, performance optimization, stability, and reliability.

[0036] As a parameterized proxy model, the neural network model usually provides standardized interfaces and APIs (Application Programming Interfaces), which make it easier and more reliable to use the neural network model in different software environments. The neural network model has a large developer community, providing a wealth of open source tools, libraries, and documentation, which speeds up the integration of the neural network model in industrial software. Using the neural network model as a proxy model can be easily embedded in existing engineering software to accelerate engineering design.

[0037] On the other hand, compared with other types of proxy models, neural network models can capture complex nonlinear relationships, are suitable for simulating and predicting the behavior of various complex systems, and have good generalization capabilities, that is, they perform well on unseen data. Using neural network models as proxy models can ensure the accuracy of calculations and predictions to a certain extent.

[0038] Therefore, the relevant technology can predict the combustion characteristics of the burner through the neural network model. However, the neural network model usually requires a large amount of training data to effectively learn the patterns and laws, especially when dealing with complex problems or high-dimensional data. For small sample points, due to insufficient data, the neural network model may overfit or fail to capture the real physical laws well, thus affecting the prediction accuracy of the burner's combustion characteristics.

[0039] In order to improve the prediction accuracy of the neural network model for the one-dimensional combustion characteristics of a porous medium burner, the present application proposes a model training method for predicting the one-dimensional combustion characteristics of a porous medium burner, a prediction method, device, electronic device, computer-readable storage medium, and computer program product for the one-dimensional combustion characteristics of a porous medium burner. Among them, the one-dimensional combustion characteristics, that is, the propagation, reaction, and heat transfer of flames and combustion waves during the combustion process are mainly carried out in one direction. In the embodiment of the present disclosure, the direction refers to the axial direction of the porous medium burner.

[0040] The following explains a model training method for predicting one-dimensional combustion characteristics of a porous medium burner, a prediction method, device, electronic device, computer-readable storage medium, and computer program product for predicting one-dimensional combustion characteristics of a porous medium burner in conjunction with the accompanying drawings.

[0041] Figure 1 A schematic flow chart of a model training method for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure.

[0042] The model training method for predicting the one-dimensional combustion characteristics of a porous medium burner can be configured to be executed in a model training device for predicting the one-dimensional combustion characteristics of a porous medium burner. The model training device for predicting the one-dimensional combustion characteristics of a porous medium burner is referred to as a model training device hereinafter. The model training device can be a server, an electronic device, or can be configured in a server or an electronic device, and this application does not limit this.

[0043] The electronic device is, for example, a computer, a tablet computer, a personal digital assistant, or other hardware device with data processing capabilities.

[0044] It should be noted that the execution subject of the embodiments of the present disclosure may be, for example, a central processing unit (CPU) in a server or electronic device in terms of hardware, or may be, for example, a related service in a server or electronic device in terms of software, without limitation.

[0045] like Figure 1 As shown, the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner includes:

[0046] S101. Modeling the combustion process of a porous medium burner of a target structure to obtain a combustion model, and determining operating parameter variables and a spatial distribution range of the operating parameter variables.

[0047] The target structure, that is, the structure of a given porous medium burner, can be designed as required, and the present disclosure does not impose any limitation on this.

[0048] In the embodiments of the present disclosure, based on the structural design and initial structural parameters of the porous media burner, tools such as Cantera can be used to use control equations to describe the physical behavior of the porous media burner during the combustion process, so as to model the combustion process of the porous media burner and obtain a combustion model.

[0049] Among them, the combustion model is based on some specific assumptions and uses single or complex physical and chemical reaction mechanisms such as gas phase and condensed phase to representatively describe the combustion process.

[0050] The control equation (specifically, partial differential equation) is a mathematical expression converted from physical phenomena such as fluid flow, heat transfer, and chemical reactions inside the burner. It can accurately describe the relationship and change law between various physical quantities (such as temperature, pressure, component concentration, etc.) during the combustion process. For example, it may include the gas phase mass conservation equation, the gas phase energy conservation equation, and the gas-solid heat transfer equation. Among them, the gas phase mass conservation equation describes the change of gas phase mass during the combustion process of the porous medium burner. The gas phase energy conservation equation describes the change of gas phase internal energy during the combustion process of the porous medium burner, including energy changes caused by convection, conduction, radiation, and chemical reactions. The gas-solid heat transfer equation describes the heat transfer between the gas phase and the solid phase due to temperature differences during the combustion process of the porous medium burner.

[0051] refer to Figure 2 The structural design and initial structural parameters of the porous medium burner can be as follows Figure 2 As shown, the total length of the porous medium burner can be 9.4 inches, including: a preheating layer formed by two first reactors, a cavity portion formed by two second reactors, a combustion zone formed by two third reactors, two fourth reactors, eight fifth reactors and two sixth reactors, and a heat reflow zone formed by two seventh reactors. Figure 22×R1 in represents two first reactors, 2×R2 represents two second reactors, and so on. PPI represents void density, which characterizes the average number of pores per unit inch length, and ε represents emissivity. Taking the cavity part as an example, it is assumed that the cavity part is a ZrO2 ring with a porosity of 0.5 and an emissivity of 0.001. The other parts are similar and will not be described in detail. The combustion process of the porous media burner of this structure is modeled using Cantera, and a combustion model can be obtained, which includes control equations such as the gas phase mass conservation equation, the gas phase energy conservation equation, and the gas-solid heat transfer equation. For example, the TPRC (Thermal Properties Research Center) data series can be used as the reference data for the thermal conductivity of the material, and is based on the thermodynamic property data provided by a certain aerospace report. The radiation thermal conductivity is calculated using the Roeesland model. For the chemical reaction mechanism, the GRI 3.0 reaction mechanism is used, and a chemical reaction network consisting of 20 reactors is constructed. It is assumed that after 3600 seconds of combustion, the system will reach a steady state.

[0052] In the disclosed embodiment, a DOE (Design of experiments) method can be used to determine the operating parameter variables and their spatial distribution range based on the lean combustion boundary and the actual operating conditions of the gas turbine. Among them, DOE is an experimental design method used to explore and verify the influence of factors on results. This method systematically plans, executes and analyzes experiments to understand how each variable affects a specific response variable, thereby optimizing product performance, improving production efficiency or reducing costs.

[0053] Among them, the operating condition parameter variable is a parameter variable used to represent the operating condition.

[0054] As an example, the operating parameter variables determined by the DOE method may include: the inlet air flow rate and the inlet chemical reaction equivalence ratio of the porous medium burner. Among them, the inlet chemical reaction equivalence ratio, which can be referred to as the equivalence ratio, is the ratio required for the reactants to react according to the stoichiometric relationship in the chemical equation in the chemical reaction. In the combustion process, this can be understood as the theoretical ratio between the fuel and the oxidant (usually oxygen in the air) required for complete combustion. The spatial distribution range of the inlet air flow rate can be 0.3-20m / s (meters / second), and the spatial distribution range of the inlet chemical reaction equivalence ratio can be 0.4-0.8.

[0055] As an example, the determined operating condition parameters may also include other operating condition parameters, such as the porosity of the porous medium burner and the structure of the porous medium burner.

[0056] S102. For multiple first sampling points in the spatial distribution range, numerical simulation is performed based on the combustion model to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner.

[0057] The axial direction of the porous medium burner is parallel to the main axis or center line of the porous medium burner. The porous medium burner includes multiple reactors arranged along the axial direction. During the combustion process, the gas flow including combustion and air flows along the axial direction. For example, Figure 2 The axial direction of the porous medium burner is horizontal.

[0058] The preset position can be set as required, for example, it can be set to the middle section of the reactor.

[0059] Among them, any sampling point in the spatial distribution range of the operating condition parameter variable corresponds to a value of the operating condition parameter variable. For example, the operating condition parameter variables include the inlet air flow rate and the inlet chemical reaction equivalence ratio of the porous medium burner, wherein the spatial distribution range of the inlet air flow rate is 0.3-20m / s, and the spatial distribution range of the inlet chemical reaction equivalence ratio is 0.4-0.8, and a certain sampling point may correspond to an inlet air flow rate of 0.4 and an inlet chemical reaction equivalence ratio of 0.5.

[0060] As an example, multiple first sampling points in the spatial distribution range of the operating condition parameter variable can be obtained in the following manner: use at least one of the following sampling methods to sample the spatial distribution range of the operating condition parameter variable to obtain multiple first candidate sampling points: Latin hypercube sampling, Sobol sampling, Kronecker sampling, random sampling; resample in the boundary area of ​​the spatial distribution range of the operating condition parameter variable to obtain multiple second candidate sampling points; use the multiple first candidate sampling points and the multiple second candidate sampling points as multiple first sampling points.

[0061] Among them, Latin hypercube sampling is a method of approximate random sampling from a multivariate parameter distribution. It divides the value range of each variable into several intervals with the same probability and randomly selects a value in each interval to ensure the randomness and uniformity of the sample.

[0062] Sobol sampling is a method for generating low-discrepancy sequences that cover the sample space more evenly than simple random sequences and thus can improve convergence speed in Monte Carlo simulations.

[0063] Kronecker sampling is another method to generate low-discrepancy sequences. It constructs sequences based on the Kronecker product and is also used to improve the efficiency of Monte Carlo simulation.

[0064] Randomness sampling refers to the uncertainty or unpredictability of data or events in statistics and computer science. In numerical analysis, randomness is often simulated by random number generators (RNGs).

[0065] As an example, the combustion model includes control equations for describing the physical behavior in the combustion process, and the control equations include: a meteorological mass conservation equation, a meteorological energy conservation equation, and a gas-solid heat transfer equation; step S102 can be implemented in the following way: for each first sampling point, based on the value of the operating parameter variable at the first sampling point, the meteorological mass conservation equation, the meteorological energy conservation equation, and the gas-solid heat transfer equation are solved to obtain a one-dimensional distribution of the temperature field of the porous medium burner at the first sampling point.

[0066] Specifically, for each first sampling point, the inlet boundary conditions and other parameters required to solve the control equation can be determined based on the value of the operating condition parameter variable at the first sampling point, and then the control equation is solved based on the inlet boundary conditions and other parameters to obtain the one-dimensional distribution of the temperature field of the porous medium burner at the first sampling point. Among them, the inlet boundary conditions may include inlet air temperature, inlet mass flow rate, etc.

[0067] Among them, the one-dimensional distribution of the temperature field of the porous medium burner at a certain sampling point can be understood as the temperature at the preset positions of multiple reactors in the axial direction of the porous medium burner when the value of the operating parameter variable is the value at the sampling point.

[0068] It should be noted that the one-dimensional distribution of the temperature field in the embodiment of the present application is obtained under given operating conditions. For example, the given operating conditions may include: using methane as fuel, its temperature is kept at room temperature, the pressure is ambient pressure, the inlet air temperature is 700K (Kelvin), etc. Under this operating condition, the one-dimensional distribution of the temperature field is calculated according to the operating parameter variables and the temperatures of the air and fuel, with respect to the fuel inlet velocity, the premixed fuel temperature and the mass flux.

[0069] S103. For multiple second sampling points in the spatial distribution range, a target interpolation method is used to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point conforms to the target physical law, and the target physical law is the law of change of the one-dimensional distribution of the temperature field with the operating condition parameter variable.

[0070] As an example, S103 can be implemented in the following manner: for each second sampling point in the spatial distribution range, a target interpolation method is used to calculate the one-dimensional distribution of the temperature field at at least one first sampling point around the second sampling point, and the one-dimensional distribution of the temperature field of the porous medium burner at the second sampling point is obtained, and the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point is made to conform to the target physical law. Thus, based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, the one-dimensional distribution of the temperature field of the porous medium burner at more sampling points can be amplified based on the target interpolation method and physical information, rather than high-fidelity numerical simulation.

[0071] The spatial distribution range of the operating condition parameter variable can be sampled at a preset interval to obtain a plurality of second sampling points. The preset interval can be set as needed, and the present disclosure does not limit this. The plurality of first sampling points are partially different from or completely different from the plurality of second sampling points.

[0072] Among them, interpolation is a method of estimating unknown data points through known data points. It estimates the approximate value of the function at other points based on the value of the function at a finite number of points. The interpolation process constructs a specific function (called the interpolation function) that is equal to the original function at the known data points and provides an approximation to the original function at other points.

[0073] The interpolation methods may include but are not limited to the following:

[0074] Polynomial interpolation: such as Lagrange interpolation, which constructs a polynomial function that is equal to the original function at known data points;

[0075] Radial basis function interpolation: Use radial basis functions (such as Gaussian functions) as basis functions and construct interpolation functions by linearly combining these basis functions. This method is often used in machine learning to process high-dimensional data and complex functions.

[0076] Spline interpolation: specifically cubic spline interpolation, which constructs a piecewise polynomial function between the data points that is a cubic polynomial in each subinterval and is smooth over the entire interval.

[0077] Among them, when the operating parameter variables include the inlet air flow rate and the inlet chemical reaction equivalence ratio of the porous medium burner, taking the outlet temperature of the porous medium burner (i.e., the temperature at the preset position of the last reactor of the porous medium burner) as an example, the target physical laws may include: for a given inlet chemical reaction equivalence ratio, as the inlet air flow rate increases, the outlet temperature of the porous medium burner shows a trend of first rising and then flattening; for a given inlet air flow rate, as the inlet chemical reaction equivalence ratio increases, the outlet temperature of the porous medium burner shows an upward trend.

[0078] The target interpolation method in the embodiment of the present disclosure is one of multiple candidate interpolation methods, wherein the multiple candidate interpolation methods may include the above-mentioned interpolation methods. The one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point obtained by using the target interpolation method conforms to the target physical law.

[0079] As an example, before S103, the target interpolation method may be determined from multiple candidate interpolation methods in the following manner:

[0080] For any candidate interpolation method and multiple fourth sampling points in the spatial distribution range, the candidate interpolation method is adopted, and based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, the one-dimensional distribution of the temperature field of the porous medium burner at each fourth sampling point is obtained;

[0081] It is determined whether the one-dimensional distribution of the temperature field of the porous medium burner at each fourth sampling point conforms to the target physical law. If so, the candidate interpolation method is determined as the target interpolation method.

[0082] Among them, the fourth sampling point is any sampling point in the spatial distribution range of the operating condition parameter variable. Multiple fourth sampling points are partially different from or completely different from multiple first sampling points. Multiple fourth sampling points can be the same as, partially different from, or completely different from multiple second sampling points.

[0083] Specifically, for each candidate interpolation method and each fourth sampling point in the spatial distribution range, the candidate interpolation method can be used to calculate the one-dimensional distribution of the temperature field at at least one first sampling point around the fourth sampling point to obtain the one-dimensional distribution of the temperature field of the porous medium burner at the fourth sampling point, and then the candidate interpolation method that can make the obtained one-dimensional distribution of the temperature field of the porous medium burner at each fourth sampling point conform to the target physical law is determined as the target interpolation method. After determining the target interpolation method from multiple candidate interpolation methods, the target interpolation method can be used to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point, where the one-dimensional distribution of the temperature field conforms to the target physical law.

[0084] As an example, in order to ensure the accuracy of the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point obtained by the target interpolation method, the accuracy of the target interpolation method can also be judged, that is, the method can also include:

[0085] For multiple third sampling points in the spatial distribution range, a target interpolation method is used to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each third sampling point based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point;

[0086] Determine that the one-dimensional distribution of the temperature field of the porous medium burner at each third sampling point conforms to the target physical law, and the difference between the one-dimensional distribution of the reference temperature field of the porous medium burner at the corresponding third sampling point is less than a preset value; wherein, the one-dimensional distribution of the reference temperature field is a one-dimensional distribution of the temperature field of the porous medium burner at the corresponding third sampling point obtained by numerical simulation based on the combustion model.

[0087] Among them, the third sampling point is any sampling point in the spatial distribution range of the operating condition parameter variable. Multiple third sampling points are partially different from or completely different from multiple first sampling points. Multiple third sampling points can be partially different from or completely different from multiple second sampling points. Multiple third sampling points can be the same as, partially different from, or completely different from multiple fourth sampling points.

[0088] Among them, the preset value can be set as needed.

[0089] It can be understood that for each third sampling point in the spatial distribution range, the control equation can be solved based on the value of the operating condition parameter variable at the third sampling point to obtain the one-dimensional distribution of the temperature field of the porous medium burner at the third sampling point. Since it is obtained through numerical simulation, the one-dimensional distribution of the temperature field can be considered to be high-fidelity numerical simulation data, and the one-dimensional distribution of the temperature field is called the reference one-dimensional distribution of the temperature field. In addition, the target interpolation method can be used to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each third sampling point based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point. Then, it is judged whether the one-dimensional distribution of the temperature field of the porous medium burner at each third sampling point conforms to the target physical law, and whether the difference between the one-dimensional distribution of the reference temperature field of the porous medium burner at the corresponding third sampling point is less than the preset value. If both are yes, it can be determined that the accuracy of the target interpolation method is high, so that the accuracy of the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point obtained by the target interpolation method is high.

[0090] S104, using the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point and each second sampling point as a training set, training the neural network model, and obtaining a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

[0091] Among them, predicting the one-dimensional combustion characteristics of the porous media burner can include predicting the one-dimensional distribution of the temperature field of the porous media burner at a certain value of the operating parameter variable, that is, when the operating parameter variable is a certain value, the temperature at the preset positions of multiple reactors in the axial direction of the porous media burner, and determining the average temperature, maximum temperature and outlet temperature of the porous media burner at the value of the operating variable based on the one-dimensional distribution of the temperature field. Among them, the average temperature is the average value of the temperatures at the preset positions of several reactors of the porous media burner; the maximum temperature is the highest value among the temperatures at the preset positions of several reactors of the porous media burner; the outlet temperature is the temperature at the preset position of the last reactor of the porous media burner. For example, with Figure 2 For example, the average temperature may be the average value of the temperature of the middle section of the 11th reactor to the temperature of the middle section of the 20th reactor; the maximum temperature may be the maximum value of the temperature of the middle section of the 11th reactor to the temperature of the middle section of the 20th reactor; and the outlet temperature may be the temperature of the middle section of the 20th reactor.

[0092] The one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point or each second sampling point is a training sample in the training set.

[0093] Among them, the neural network model can be any type of neural network model such as a deep neural network, a convolutional neural network, etc.

[0094] In an embodiment of the present disclosure, the sampling point corresponding to each training sample, that is, the value of the operating parameter variable at the sampling point, can be used as the input of the neural network model. The one-dimensional distribution of the temperature field of the porous medium burner at the sampling point is predicted by the neural network model, and the predicted one-dimensional distribution of the temperature field is compared with the known one-dimensional distribution of the temperature field corresponding to the training sample. Based on the degree of deviation between the predicted one-dimensional distribution of the temperature field of all training samples in the training set and the known one-dimensional distribution of the temperature field, the model parameters of the neural network model are adjusted, thereby realizing the training of the neural network model and obtaining a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

[0095] Take a deep feedforward neural network as an example, where "feedforward" means that physical information flows from the input x, flows through the intermediate function used to define f, and finally reaches the output y, without feedback connections from the output to each connection layer. A deep feedforward neural network defines a mapping function y = f(x; θ) and learns the value of the parameter θ from the training set, including the weight W (i) and deviation b (i) , that is, {W (i) and b (i) , i = 1, 2, ... l}, by selecting a suitable loss function, the predicted result is as close to the actual value as possible. The function f is expressed as follows:

[0096] y=f(x;θ)=f (l) (f l- 1(...f 2 (f 1 )))(1)

[0097] Among them, f 1 is called the input layer of the neural network model, f l It is called the output layer of the neural network model, and the total length l of the chain represents the depth of the neural network model, that is, the number of layers of the neural network model.

[0098] i-th th The weight matrix W of the layer (i) It can be expressed as follows:

[0099]

[0100] in, represents (i-1) th Layer (n (i-1) ) th Neuron to i th Layer (n (i) ) th The connection weights between neurons, n (i) Representative th The number of neurons in the layer.

[0101] i-th th The deviation vector b (i) The expression is as follows:

[0102]

[0103] in, Represents the i th Layer (n (i) ) th Neuronal bias.

[0104] i thThe intermediate information carried by the neurons in the layer, i.e. the output h (i) It can be defined as:

[0105] h (i) =σ i (W (i) h (i-1) +b (i) ) (4)

[0106] Among them, σ i Indicates i th The activation function of the layer. The activation function is the key to simulating the nonlinearity of the neural network. The ReLU activation function can be selected.

[0107] Given a training set N train , the loss function J(θ) can be used to evaluate the degree of deviation between the predicted value (i.e., the one-dimensional distribution of the temperature field predicted in the aforementioned embodiment) and the actual value (i.e., the one-dimensional distribution of the known temperature field in the aforementioned embodiment) on the entire training set:

[0108]

[0109] Where N train is the number of training samples included in the training set, y train Indicates the actual value, y * Represents the predicted value of the neural network model.

[0110] The model training method for predicting the one-dimensional combustion characteristics of a porous medium burner provided by the present invention models the combustion process of a porous medium burner of a target structure to obtain a combustion model, performs numerical simulation based on the combustion model, and obtains a one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, thereby achieving the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point through high-fidelity numerical simulation, and obtains the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point by adopting a target interpolation method, which can effectively amplify the sampling The number of sample points is increased, thereby expanding the number of training samples in the training set and improving the generalization ability of the target prediction model. The one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point conforms to the target physical law, and realizes the coupling of physical information on the basis of high-fidelity numerical simulation. Therefore, the target prediction model obtained by training the neural network model based on the training set can better approximate the target physical law when predicting the one-dimensional combustion characteristics of the porous medium burner, avoid the deviation from the physical law under the condition of a small sample number, and achieve more accurate prediction accuracy, thereby realizing the same function as PINN (Physics-informed neural network).

[0111] It should be noted that, since the target prediction model obtained by training the neural network based on the training set in the embodiment of the present disclosure has the same function as PINN, the target prediction model in the embodiment of the present disclosure may also be referred to as PINN. In addition, in the embodiment of the present disclosure, after obtaining the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point and each second sampling point, the one-dimensional distribution of the temperature field may be corrected based on high-precision experimental data and additional high-fidelity numerical simulation to generate a higher quality training set, ensuring that the target prediction model obtained by training based on the training set can follow the relevant physical laws and have stronger generalization ability.

[0112] Based on the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner provided in the above-mentioned embodiment, an embodiment of the present disclosure further provides a method for predicting the one-dimensional combustion characteristics of a porous medium burner.

[0113] Combine the following Figure 3 , the prediction method of the one-dimensional combustion characteristics of the porous medium burner provided in the embodiment of the present application is further explained.

[0114] Figure 3 A schematic flow chart of a method for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure.

[0115] like Figure 3 As shown, the prediction method of the one-dimensional combustion characteristics of the porous medium burner includes:

[0116] S301, obtaining a target prediction model.

[0117] Among them, the target prediction model can be trained based on the method in the above embodiment.

[0118] S302. Use the target prediction model to predict the one-dimensional combustion characteristics of the porous medium burner to obtain the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner.

[0119] The target value can be any value of the operating condition parameter variable.

[0120] Among them, the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable can be understood as the temperature at the preset positions of multiple reactors in the axial direction of the porous medium burner when the value of the operating parameter variable is the target value.

[0121] In the embodiment of the present disclosure, the target value of the operating parameter variable is input into the target prediction model, so as to obtain the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable.

[0122] It should be noted that the one-dimensional combustion characteristics of the porous media burner predicted by the embodiment of the present disclosure may be the one-dimensional combustion characteristics of the porous media burner under any operating conditions, which may be the same as or different from the operating conditions during the training process of the target prediction model.

[0123] S303, based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, determine the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value.

[0124] The average temperature is the average temperature of the preset positions of several reactors of the porous medium burner; the maximum temperature is the highest value among the temperatures of the preset positions of several reactors of the porous medium burner; and the outlet temperature is the temperature of the preset position of the last reactor of the porous medium burner. Figure 2 For example, the average temperature may be the average value of the temperature of the middle section of the 11th reactor to the temperature of the middle section of the 20th reactor; the maximum temperature may be the maximum value of the temperature of the middle section of the 11th reactor to the temperature of the middle section of the 20th reactor; and the outlet temperature may be the temperature of the middle section of the 20th reactor.

[0125] It should be noted that in the embodiment of the present disclosure, a response surface model between the operating parameter variables and the average temperature, maximum temperature and outlet temperature of the porous medium burner can be constructed based on the target prediction model. Such a model can quickly and accurately predict the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value after the target value of the operating parameter variable is given, thereby supporting the iterative optimization of the structure and operating parameter variables of the porous medium burner. Among them, the response surface model can be composed of a target prediction model and a temperature calculation module. The target prediction model can quickly and accurately predict the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable based on the target value of the operating parameter variable. The temperature calculation module can determine the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value based on the one-dimensional temperature distribution.

[0126] In summary, the method for predicting the one-dimensional combustion characteristics of a porous medium burner provided in the embodiment of the present invention predicts the one-dimensional combustion characteristics of the porous medium burner by adopting a target prediction model, and obtains the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner, and based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value are determined, thereby realizing rapid prediction of the one-dimensional combustion characteristics of the porous medium burner based on the target prediction model, and being able to better approximate the target physical laws during prediction, avoiding deviation from the physical laws under conditions of small sample quantities, and achieving more accurate prediction accuracy.

[0127] The following describes the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner, the prediction method for the one-dimensional combustion characteristics of a porous medium burner, and the prediction accuracy of the prediction method provided by the embodiment of the present disclosure in conjunction with the accompanying drawings. Fig.11 This is a cloud diagram of the actual changes in the average temperature, maximum temperature and outlet temperature of the porous medium burner with the inlet air flow rate and equivalence ratio within the range of 0.3-20m / s and equivalence ratio of 0.4-0.8.

[0128] First, the combustion process of the porous medium burner of the target structure can be modeled to obtain a combustion model, and the operating parameter variables and the spatial distribution range of the operating parameter variables can be determined. Among them, the structural design and initial structural parameters of the porous medium burner can be, for example, Figure 2 The operating parameters include the inlet air velocity u and the inlet chemical reaction equivalence ratio of the porous medium burner. The spatial distribution range of the inlet air velocity is 0.3-20 m / s, and the spatial distribution range of the inlet chemical reaction equivalence ratio is 0.4-0.8.

[0129] Then, Latin hypercube sampling can be used to sample the spatial distribution range of the operating condition parameter variable to obtain multiple first candidate sampling points, and resampling can be performed in the boundary area of ​​the spatial distribution range of the operating condition parameter variable to obtain multiple second candidate sampling points, and the multiple first candidate sampling points and the multiple second candidate sampling points are used as multiple first sampling points. The distribution of the first candidate sampling points in the spatial distribution range of the operating condition parameter variable is as follows: Figure 4 The distribution of multiple first candidate sampling points and multiple second candidate sampling points in the spatial distribution range of the operating condition parameter variable is shown in Figure (a). Figure 4 As shown in Figure (b), Figure 4The red circle in Figure (b) represents the first candidate sampling point, and the blue circle represents the second candidate sampling point.

[0130] Next, for multiple first sampling points in the spatial distribution range, numerical simulation can be performed based on the combustion model to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner.

[0131] Furthermore, the spatial distribution range of the operating condition parameter variable can be sampled at preset intervals to obtain a plurality of second sampling points. The distribution of the plurality of second sampling points in the spatial distribution range of the operating condition parameter variable is as follows: Figure 4 As shown in Figure (c), Figure 4 The red circle in Figure (c) represents the first sampling point, and the blue box represents the second sampling point.

[0132] Furthermore, for multiple second sampling points in the spatial distribution range, a target interpolation method can be used to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point conforms to the target physical law, and the target physical law is the law of change of the one-dimensional distribution of the temperature field with the operating condition parameter variable. That is, the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point is obtained by reasonably selecting the interpolation method and combining physical information, rather than by high-fidelity numerical simulation. Among them, Figure 5 is a schematic diagram of the temperature response surface obtained based on physical information, including the outlet temperature of the porous medium burner at each first sampling point and each second sampling point. Figure 5 The z-axis is the outlet temperature (T) of the porous media burner, in Kelvin K. Figure 5 It can be seen that for a given equivalence ratio θ, as the inlet air flow rate u increases, the outlet temperature T shows a trend of first rising and then leveling off. For a given inlet air flow rate u, as the equivalence ratio θ increases, the outlet temperature T shows a trend of rising, which is in line with the target physical law. Figure 5 The outlet temperatures corresponding to the sampling points other than the second sampling point and the first sampling point are compared with the outlet temperatures corresponding to the sampling points obtained based on numerical simulation, and the results are similar. This proves that the target interpolation method can effectively expand the number of sampling points while ensuring that the outlet temperature at each second sampling point conforms to the target physical law, thereby expanding the number of training samples in the training set and ensuring the generalization ability of the deep neural network.

[0133] In the disclosed embodiment, a deep neural network and a Gaussian process can be used as proxy models respectively, and the one-dimensional distribution of the temperature field of the porous medium burner at each first candidate sampling point is used as a training set. The proxy models of the deep neural network and the Gaussian process are trained respectively to obtain the trained proxy models, and based on the trained proxy models, the average temperature, maximum temperature and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variables are predicted respectively. Among them, Figure 6 It is a structural diagram of the deep neural network model. Figure 6 x1, x2, ..., x Din Represents different characteristics of the input data, Figure 6 in y1, y2, y3, y4,…,y Dout Respectively represent the temperature at a preset position of each reactor in the axial direction of the output porous medium burner. Figure 7 Figures (a), (b), and (c) respectively represent the average temperature, maximum temperature, and outlet temperature of the porous media burner at multiple values ​​of the operating parameter variables when the deep neural network is used as the proxy model and the one-dimensional distribution of the temperature field of the porous media burner at each first candidate sampling point is used as the training set. Figure 8 Figures (a), (b), and (c) in the figure respectively represent the average temperature, maximum temperature, and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variable when the Gaussian process is used as the proxy model and the one-dimensional distribution of the temperature field of the porous medium burner at each first candidate sampling point is used as the training set. The results show that the prediction law of the proxy model using the Gaussian process does not conform to the target physical law, and only captures the distribution of the temperature field in a small area near the training sample point. The proxy model using the deep neural network can better capture the spatial distribution of the temperature field, which is consistent with the target physical law to a certain extent, but there is still a large predicted temperature difference near the boundary, which is inconsistent with the theoretical results.

[0134] In the embodiment of the present disclosure, a deep neural network can also be used as a proxy model, and the one-dimensional distribution of the temperature field of the porous medium burner at each first candidate sampling point and each second candidate sampling point is used as a training set, and the proxy model of the deep neural network is trained respectively to obtain a trained proxy model, and based on the trained proxy model, the predicted Fig. 9 The average temperature, maximum temperature and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variables are shown. Fig. 9 Figures (a), (b), and (c) in the figure represent the average temperature, maximum temperature, and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variables. Fig. 9It can be seen that compared with only using the one-dimensional distribution of the temperature field of the porous medium burner at each first candidate sampling point as the training set, using the one-dimensional distribution of the temperature field of the porous medium burner at each first candidate sampling point and each second candidate sampling point as the training set effectively improves the prediction accuracy of the deep neural network near the boundary, and the overall trend is consistent with the existing physical information, but there are still some areas (such as for the highest temperature, in the area where the inlet air flow rate is low, the equivalence ratio is 0.4-0.5, 0.7-0.8, as the inlet air flow rate changes, the development trend of the highest temperature does not conform to the target physical law). On the other hand, compared with Fig.11 Compared with the existing high-fidelity numerical simulation results shown in the figure, there is still a certain prediction error.

[0135] In the embodiment of the present disclosure, a deep neural network can be used as a proxy model, and the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point and each second sampling point is used as a training set. The proxy model of the deep neural network is trained respectively to obtain a trained proxy model (i.e., the target prediction model in the embodiment of the present disclosure), and based on the trained proxy model, the target prediction model is predicted respectively. Fig.10 The average temperature, maximum temperature and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variables are shown. Fig.10 Figures (a), (b), and (c) in the figure represent the average temperature, maximum temperature, and outlet temperature of the porous medium burner at multiple values ​​of the operating parameter variables. Fig.11 By comparison, the results show that the target prediction model can better capture the distribution of the temperature field in the design space and conform to the relevant physical laws. Therefore, it can be proved that the target prediction model will not deviate from the basic physical laws controlled by the control equation under a small sample size, and has high prediction accuracy and generalization ability.

[0136] In summary, no matter which training set is used, using deep neural network as a proxy model, compared with other proxy models, can achieve fast and accurate prediction of the corresponding average temperature, maximum temperature and outlet temperature after given the value of new operating parameter variables, thereby supporting the iterative optimization of the porous medium burner structure and operating parameter variables. On the other hand, using the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point and each second sampling point as a training set, using deep neural network as a proxy model, by considering the physical meaning of the data, and implementing data enhancement through interpolation and other methods, additional physical information constraints are introduced, which can ensure that the deep neural network fits the physical laws more accurately in these key areas, effectively improving the generalization ability and prediction accuracy of the model.

[0137] Fig.12A schematic diagram of the structure of a model training device for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure.

[0138] like Fig.12 As shown, the model training device 1200 for predicting the one-dimensional combustion characteristics of a porous medium burner comprises:

[0139] A modeling module 1210 is used to model the combustion process of the porous medium burner of the target structure, obtain a combustion model, and determine the operating parameter variables and the spatial distribution range of the operating parameter variables;

[0140] The simulation module 1220 is used to perform numerical simulation based on the combustion model for a plurality of first sampling points in the spatial distribution range, and obtain a one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, wherein the one-dimensional distribution of the temperature field includes the temperature at a plurality of preset positions of the reactors in the axial direction of the porous medium burner;

[0141] The acquisition module 1230 is used to acquire the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point by adopting a target interpolation method for a plurality of second sampling points in the spatial distribution range, based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point conforms to a target physical law, and the target physical law is a law of variation of the one-dimensional distribution of the temperature field with a variable of an operating condition parameter;

[0142] The training module 1240 is used to train the neural network model using the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point and each second sampling point as a training set to obtain a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

[0143] It should be noted that the aforementioned explanation of the model training method for predicting the one-dimensional combustion characteristics of a porous medium burner is also applicable to the model training device for predicting the one-dimensional combustion characteristics of a porous medium burner in this embodiment, and will not be repeated here.

[0144] In some embodiments, the model training device 1200 for predicting one-dimensional combustion characteristics of a porous medium burner further includes:

[0145] A first sampling module is used to sample the spatial distribution range of the operating condition parameter variable by using at least one of the following sampling methods to obtain a plurality of first candidate sampling points: Latin hypercube sampling, Sobol sampling, Kronecker sampling, and random sampling;

[0146] A second sampling module is used to resample in a boundary area of ​​the spatial distribution range of the operating condition parameter variable to obtain a plurality of second candidate sampling points;

[0147] The sampling point determination module is used to use the multiple first candidate sampling points and the multiple second candidate sampling points as the multiple first sampling points.

[0148] In some embodiments, the combustion model includes control equations for describing physical behavior during the combustion process, the control equations including: a meteorological mass conservation equation, a meteorological energy conservation equation, and a gas-solid heat transfer equation; a simulation module 1220 for:

[0149] For each first sampling point, based on the values ​​of the operating parameter variables at the first sampling point, the meteorological mass conservation equation, the meteorological energy conservation equation and the gas-solid heat transfer equation are solved to obtain the one-dimensional distribution of the temperature field of the porous medium burner at the first sampling point.

[0150] In some embodiments, the acquisition module is further used to acquire the one-dimensional distribution of the temperature field of the porous medium burner at each third sampling point by adopting a target interpolation method for multiple third sampling points in the spatial distribution range based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point;

[0151] The model training device 1200 for predicting one-dimensional combustion characteristics of a porous medium burner further includes:

[0152] An accuracy determination module is used to determine whether the one-dimensional distribution of the temperature field of the porous medium burner at each third sampling point conforms to the target physical law, and the difference between the one-dimensional distribution of the reference temperature field of the porous medium burner at the corresponding third sampling point is less than a preset value; wherein the one-dimensional distribution of the reference temperature field is a one-dimensional distribution of the temperature field of the porous medium burner at the corresponding third sampling point obtained by numerical simulation based on the combustion model.

[0153] In this embodiment, by modeling the combustion process of the porous medium burner of the target structure, a combustion model is obtained, and numerical simulation is performed based on the combustion model to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, so that the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point is obtained through high-fidelity numerical simulation. By adopting the target interpolation method, based on the one-dimensional distribution of the temperature field of the porous medium burner at each first sampling point, the one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point is obtained, which can effectively expand the number of sampling points, thereby expanding the number of training samples in the training set, and improving the generalization ability of the target prediction model. The one-dimensional distribution of the temperature field of the porous medium burner at each second sampling point conforms to the target physical law, and realizes the coupling of physical information on the basis of high-fidelity numerical simulation, so that the target prediction model obtained by training the neural network model based on the training set can better approximate the target physical law when predicting the one-dimensional combustion characteristics of the porous medium burner, avoid the deviation from the physical law under the condition of a small sample number, and achieve more accurate prediction accuracy, thereby achieving the same as PINN (Physics-informed neural network). network, physically informed neural network models) with the same functionality.

[0154] Fig.13 A schematic diagram of the structure of a device for predicting one-dimensional combustion characteristics of a porous medium burner provided in an embodiment of the present disclosure.

[0155] like Fig.13 As shown, the prediction device 1300 for the one-dimensional combustion characteristics of the porous medium burner includes:

[0156] An acquisition module 1310 is used to acquire a target prediction model, wherein the target prediction model is trained based on the model training method for predicting one-dimensional combustion characteristics of a porous medium burner in the aforementioned embodiment;

[0157] A prediction module 1320 is used to predict the one-dimensional combustion characteristics of the porous medium burner by using a target prediction model, and obtain a one-dimensional distribution of the temperature field of the porous medium burner at a target value of the operating parameter variable, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner;

[0158] The temperature determination module 1330 is used to determine the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable.

[0159] It should be noted that the aforementioned explanation of the method for predicting the one-dimensional combustion characteristics of a porous medium burner is also applicable to the device for predicting the one-dimensional combustion characteristics of a porous medium burner of this embodiment, and will not be repeated here.

[0160] In this embodiment, the one-dimensional combustion characteristics of the porous medium burner are predicted by adopting a target prediction model, and the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable is obtained, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner. Based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value are determined, thereby realizing rapid prediction of the one-dimensional combustion characteristics of the porous medium burner based on the target prediction model, and being able to better approximate the target physical laws during prediction, avoiding deviation from the physical laws under conditions of small sample numbers, and achieving more accurate prediction accuracy.

[0161] Fig.14 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Fig.14 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0162] like Fig.14 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 that connects various system components (including the memory 28 and the processing unit 16).

[0163] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0164] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0165] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig.14 Not shown, often called a "hard drive").

[0166] although Fig.14 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (hereinafter referred to as: CD-ROM), a digital versatile disc read only memory (hereinafter referred to as: DVD-ROM) or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0167] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0168] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable the human body to interact with the electronic device 12, and / or any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. Fig.14 As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although Fig.14 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0169] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing the model training method for predicting the one-dimensional combustion characteristics of the porous medium burner mentioned in the above embodiment.

[0170] In order to implement the above-mentioned embodiments, the present disclosure also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the model training method for predicting the one-dimensional combustion characteristics of a porous media burner as proposed in the aforementioned embodiments of the present disclosure.

[0171] In order to implement the above embodiments, the present disclosure also proposes a computer program product. When the instructions in the computer program product are executed by a processor, the model training method for predicting the one-dimensional combustion characteristics of a porous media burner proposed in the above embodiments of the present disclosure is executed.

[0172] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this disclosure shall comply with the relevant laws and regulations and shall not violate public order and good morals.

[0173] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0174] The present disclosure anticipates providing implementation schemes for users to selectively block the use or access of personal information data. That is, the present disclosure anticipates providing hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0175] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0176] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0177] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0178] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0179] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0180] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0181] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0182] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A model training method for predicting one-dimensional combustion characteristics of a porous media burner, characterized in that: The method comprises: Modeling the combustion process of the porous medium burner of the target structure to obtain a combustion model, and determining operating parameter variables and the spatial distribution range of the operating parameter variables; For a plurality of first sampling points in the spatial distribution range, numerical simulation is performed based on the combustion model to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, wherein the one-dimensional distribution of the temperature field includes the temperatures at preset positions of a plurality of reactors in the axial direction of the porous medium burner; For a plurality of second sampling points in the spatial distribution range, a target interpolation method is adopted to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points based on the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points conforms to a target physical law, and the target physical law is a law of variation of the one-dimensional distribution of the temperature field with the operating condition parameter variable; The one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points and each of the second sampling points is used as a training set to train the neural network model to obtain a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

2. The method according to claim 1, characterized in that The method further comprises: At least one of the following sampling methods is used to sample the spatial distribution range of the operating condition parameter variable to obtain a plurality of first candidate sampling points: Latin hypercube sampling, Sobol sampling, Kronecker sampling, and random sampling; Resampling is performed in a boundary area within the spatial distribution range of the operating condition parameter variable to obtain a plurality of second candidate sampling points; The multiple first candidate sampling points and the multiple second candidate sampling points are used as the multiple first sampling points.

3. The method according to claim 1, characterized in that The combustion model includes control equations for describing physical behaviors in the combustion process, and the control equations include: a meteorological mass conservation equation, a meteorological energy conservation equation, and a gas-solid heat transfer equation; The method of performing numerical simulation based on the combustion model for a plurality of first sampling points in the spatial distribution range to obtain a one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points includes: For each of the first sampling points, based on the value of the operating parameter variable at the first sampling point, the meteorological mass conservation equation, the meteorological energy conservation equation and the gas-solid heat transfer equation are solved to obtain a one-dimensional distribution of the temperature field of the porous medium burner at the first sampling point.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: For a plurality of third sampling points in the spatial distribution range, the target interpolation method is adopted to obtain the one-dimensional distribution of the temperature field of the porous medium burner at each of the third sampling points based on the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points; Determine that the one-dimensional distribution of the temperature field of the porous medium burner at each of the third sampling points conforms to the target physical law, and the difference between the one-dimensional distribution of the reference temperature field of the porous medium burner at the corresponding third sampling point is less than a preset value; wherein the one-dimensional distribution of the reference temperature field is a one-dimensional distribution of the temperature field of the porous medium burner at the corresponding third sampling point obtained by numerical simulation based on the combustion model.

5. A method for predicting one-dimensional combustion characteristics of a porous medium burner, characterized in that: include: Obtaining a target prediction model, wherein the target prediction model is trained based on the method according to any one of claims 1 to 4; The target prediction model is used to predict the one-dimensional combustion characteristics of the porous medium burner to obtain a one-dimensional distribution of the temperature field of the porous medium burner at a target value of an operating parameter variable, wherein the one-dimensional distribution of the temperature field includes temperatures at preset positions of multiple reactors in the axial direction of the porous medium burner; Based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, the average temperature, the maximum temperature and the outlet temperature of the porous medium burner at the target value point are determined.

6. A model training device for predicting one-dimensional combustion characteristics of a porous medium burner, characterized in that: include: A modeling module, used to model the combustion process of a porous medium burner of a target structure, obtain a combustion model, and determine operating parameter variables and a spatial distribution range of the operating parameter variables; A simulation module, for performing numerical simulation based on the combustion model for a plurality of first sampling points in the spatial distribution range, to obtain a one-dimensional distribution of a temperature field of the porous medium burner at each of the first sampling points, wherein the one-dimensional distribution of the temperature field includes temperatures at preset positions of a plurality of reactors in the axial direction of the porous medium burner; an acquisition module, for acquiring the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points by adopting a target interpolation method for a plurality of second sampling points in the spatial distribution range, based on the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points, wherein the one-dimensional distribution of the temperature field of the porous medium burner at each of the second sampling points conforms to a target physical law, and the target physical law is a law of variation of the one-dimensional distribution of the temperature field with the operating condition parameter variable; A training module is used to train a neural network model using the one-dimensional distribution of the temperature field of the porous medium burner at each of the first sampling points and each of the second sampling points as a training set to obtain a target prediction model for predicting the one-dimensional combustion characteristics of the porous medium burner.

7. A device for predicting one-dimensional combustion characteristics of a porous medium burner, characterized in that: include: An acquisition module, used to acquire a target prediction model, wherein the target prediction model is trained based on the method according to any one of claims 1 to 4; A prediction module, used to predict the one-dimensional combustion characteristics of the porous medium burner by using the target prediction model, and obtain the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable, wherein the one-dimensional distribution of the temperature field includes the temperatures at the preset positions of multiple reactors in the axial direction of the porous medium burner; The temperature determination module is used to determine the average temperature, maximum temperature and outlet temperature of the porous medium burner at the target value based on the one-dimensional distribution of the temperature field of the porous medium burner at the target value of the operating parameter variable.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 4, or to implement the method according to claim 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4, or the method according to claim 5 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4, or implements the method according to claim 5.

Images