Combustion chamber simulation model parameter optimization method, device, equipment and medium

Abstract

The invention relates to the technical field of combustion chamber three-dimensional numerical simulation, and particularly provides a combustion chamber simulation model parameter optimization method, device, equipment and medium, and the method comprises the steps: determining a sample model parameter set according to the initial parameter range of a plurality of model parameters of a plurality of combustion chamber simulation models; performing combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of a plurality of combustion chamber performance parameters; based on the sample model parameter set and the simulation result data set, constructing a target quantity agent model of each combustion chamber performance parameter about a plurality of model parameters; constructing a multi-objective optimization problem mathematical model based on the target quantity agent models of the plurality of combustion chamber performance parameters about the plurality of model parameters and the constraint conditions, and performing parameter optimization by using an optimization algorithm to obtain an optimal parameter solution set of the plurality of model parameters; the reliability of the determined optimal parameter solution set of the multiple model parameters can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of three-dimensional numerical simulation of combustion chambers, and in particular to a method, device, equipment and medium for optimizing parameters of a combustion chamber simulation model. Background Art

[0002] The combustion chamber is one of the three core components of an aircraft engine. It is the core area where oil-gas mixing and chemical reactions occur. The quality of its design is directly related to the overall performance of the engine. Due to the complex physical and chemical process characteristics in the combustion chamber, it is necessary to specifically select physical models such as atomization, evaporation, turbulence and combustion to carry out multi-model coupled simulation calculations.

[0003] In the related art, before simulating the combustion chamber, it is necessary to optimize the model parameters of multiple selected physical models to determine appropriate model parameter values, thereby improving the accuracy of the combustion chamber simulation.

[0004] However, in the related art, when optimizing the model parameters of multiple physical models, attention is usually paid to the influence of a small number of model parameters of a single physical model on the combustion chamber simulation results, which cannot meet the actual needs of joint simulation of multiple physical models, resulting in low accuracy of the determined combustion chamber simulation. Summary of the invention

[0005] The present disclosure is proposed in view of the above problems. The present disclosure provides a combustion chamber simulation model parameter optimization method, device, equipment and medium, which can improve the reliability of the optimal parameter solution set of multiple model parameters to ensure the accuracy of the combustion chamber simulation results determined based on the optimal parameter solution set of multiple model parameters.

[0006] According to one aspect of the present disclosure, a method for optimizing parameters of a combustion chamber simulation model is provided, comprising:

[0007] Determining a sample model parameter set according to initial parameter ranges of multiple model parameters of multiple combustion chamber simulation models;

[0008] Performing simulation calculation of the combustion chamber based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters;

[0009] Based on the sample model parameter set and the simulation result data set, constructing a target quantity proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters;

[0010] A mathematical model of a multi-objective optimization problem is constructed based on target quantity proxy models of multiple combustion chamber performance parameters respectively related to the multiple model parameters, and constraint conditions, and an optimization algorithm is used to perform parameter optimization to obtain an optimal parameter solution set for the multiple model parameters.

[0011] According to another aspect of the present disclosure, a combustion chamber simulation model parameter optimization device is provided, comprising:

[0012] a determination module configured to determine a sample model parameter set according to initial parameter ranges of a plurality of model parameters of a plurality of combustion chamber simulation models;

[0013] A simulation module, configured to perform simulation calculation of the combustion chamber based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters;

[0014] A construction module configured to construct a target amount proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters based on the sample model parameter set and the simulation result data set;

[0015] The determination module is configured to construct a mathematical model of a multi-objective optimization problem based on target quantity proxy models of the plurality of combustion chamber performance parameters respectively related to the plurality of model parameters, and constraint conditions, and use an optimization algorithm to perform parameter optimization to obtain an optimal parameter solution set for the plurality of model parameters.

[0016] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-mentioned combustion chamber simulation model parameter optimization method.

[0017] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned combustion chamber simulation model parameter optimization method is implemented.

[0018] The combustion chamber simulation model parameter optimization method, device, equipment and medium provided by the present invention can construct a target quantity proxy model of each combustion chamber performance parameter with respect to multiple model parameters for a combustion chamber simulation scenario involving multiple combustion chamber simulation models and multiple combustion chamber performance parameters, and construct a mathematical model of a multi-objective optimization problem in combination with constraint conditions, and use an optimization algorithm to perform parameter optimization to determine the optimal parameter solution set of the multiple model parameters. Since the optimization process simultaneously optimizes multiple model parameters of multiple combustion chamber simulation models, the reliability of the optimal parameter solution set of the multiple model parameters can be improved to ensure the accuracy of the combustion chamber simulation results determined based on the optimal parameter solution set of multiple model parameters.

[0019] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0021] Figure 1 is a flow chart illustrating a method for optimizing parameters of a combustion chamber simulation model according to an embodiment of the present disclosure.

[0022] Figure 2 It is a flowchart that further illustrates the determination of the target quantity proxy model in the combustion chamber simulation model parameter optimization method of the embodiment of the present disclosure.

[0023] Figure 3 It is a flowchart further illustrating the determination of the optimal parameter solution set for multiple model parameters in the combustion chamber simulation model parameter optimization method according to the embodiment of the present disclosure.

[0024] Figure 4 is a flow chart illustrating another combustion chamber simulation model parameter optimization method according to an embodiment of the present disclosure.

[0025] Figure 5 is a schematic diagram illustrating a combustion chamber simulation result applied according to an embodiment of the present disclosure.

[0026] Figure 6 It is a schematic diagram illustrating a combustion chamber simulation result according to the related art.

[0027] Figure 7 is a block diagram illustrating a combustion chamber simulation model parameter optimization device according to an embodiment of the present disclosure.

[0028] Figure 8 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure.

[0029] Fig. 9 is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0031] In order to solve the above problems, the embodiment of the present disclosure provides a combustion chamber simulation model parameter optimization method, which can be applied to a terminal device, which can be an electronic device such as a computer, a notebook or a server, such as Figure 1 As shown, the combustion chamber simulation model parameter optimization method includes:

[0032] Step S101, determining a sample model parameter set according to initial parameter ranges of multiple model parameters of multiple combustion chamber simulation models;

[0033] Step S102, performing combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters;

[0034] Step S103, constructing a target quantity proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters based on the sample model parameter set and the simulation result data set;

[0035] Step S104, constructing a mathematical model of a multi-objective optimization problem based on target quantity proxy models of the plurality of combustion chamber performance parameters respectively related to the plurality of model parameters and constraint conditions, and performing parameter optimization using an optimization algorithm to obtain an optimal parameter solution set of the plurality of model parameters.

[0036] To summarize, the combustion chamber simulation model parameter optimization method provided by the disclosed example can construct a target quantity proxy model of each combustion chamber performance parameter with respect to multiple model parameters for a combustion chamber simulation scenario involving multiple combustion chamber simulation models and multiple combustion chamber performance parameters, and construct a mathematical model of a multi-objective optimization problem in combination with constraint conditions, and use an optimization algorithm to perform parameter optimization to determine the optimal parameter solution set of multiple model parameters. Since the optimization process simultaneously optimizes multiple model parameters of multiple combustion chamber simulation models, the reliability of the optimal parameter solution set of the determined multiple model parameters can be improved to ensure the accuracy of the combustion chamber simulation results determined based on the optimal parameter solution set of multiple model parameters.

[0037] The following Figure 1 The specific implementation methods of each step in the embodiment shown are described in detail:

[0038] In step S101, the terminal device determines a sample model parameter set according to initial parameter ranges of multiple model parameters of multiple combustion chamber simulation models.

[0039] In the embodiment of the present disclosure, the combustion chamber simulation model is a physical model that can be used for combustion chamber simulation, and the model parameters are parameters related to the combustion chamber simulation model; it can be understood that multiple combustion chamber simulation models and the initial parameter ranges of multiple model parameters can be determined based on actual needs, and the embodiment of the present disclosure does not limit this.

[0040] For example, in a combustion chamber simulation transient calculation scenario, the optional combustion chamber simulation model, the model parameters related to the combustion chamber simulation model, and the initial parameter range can be as shown in Table 1; and, in a combustion chamber simulation steady-state calculation scenario, the optional combustion chamber simulation model, the model parameters related to the combustion chamber simulation model, and the initial parameter range can be as shown in Table 2.

[0041] Table 1

[0042]

[0043] Table 2

[0044]

[0045] In an optional embodiment, before determining the sample model parameter set based on the initial parameter ranges of multiple model parameters of multiple combustion chamber simulation models, the terminal device may also: in response to obtaining a combustion chamber simulation instruction, determine the multiple combustion chamber simulation models selected by the combustion chamber simulation instruction and the initial parameter ranges of the multiple model parameters obtained in the combustion chamber simulation model configuration information table; further, determine the sample model parameter set based on the initial parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models.

[0046] In an optional embodiment, the process of determining the sample model parameter set according to the initial parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models by the terminal device may include: normalizing the initial parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models to obtain the normalized parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models; further, repeating the optimal Latin hypercube sampling in the normalized parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models to obtain the candidate model parameter set, and determining the system potential energy of the candidate model parameter set based on the AE (Audze–Eglais) potential energy criterion, and determining the candidate model parameter set with the smallest system potential energy in the candidate model parameter set obtained by multiple samplings as the sample model parameter set. Based on the AE potential energy criterion, a data set with the best sample quality can be selected as the sample model parameter set in the parameter ranges of the multiple model parameters, so that the target quantity proxy model of the combustion chamber performance parameters constructed based on the sample model parameter set with respect to the multiple model parameters is more accurate.

[0047] The process of determining the system potential of the candidate model parameter set based on the AE potential criterion can be implemented based on the first formula, wherein the first formula is:

[0048]

[0049] In formula 1, U(x) is the potential energy of the system, x i is the i-th sample value associated with a model parameter in the candidate model parameter set, x i is the jth sample value related to the same model parameter in the candidate model parameter set, N is the total number of sample values ​​related to multiple model parameters, ||x i -x j || 2 is the Euclidean distance between the i-th sample value and the j-th sample value associated with the same model parameter.

[0050] It should be noted that the sample model parameter set may include multiple groups of model parameter subsets, wherein each group of model parameter subsets includes sample values ​​of multiple model parameters.

[0051] For example, the sample model parameter set can be expressed as Wherein, the number of model parameters is m, the number of sample values ​​of each model parameter is p, and the sample model parameter set may include p groups of model parameter subsets.

[0052] Step S102: The terminal device performs combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters.

[0053] In the embodiments of the present disclosure, combustion chamber simulation calculations may be implemented based on simulation software; multiple combustion chamber performance parameters may include combustion chamber pressure loss, combustion efficiency, and outtemperature distribution factor (OTDF), etc. Specifically, they may be determined based on actual needs, and the embodiments of the present disclosure do not limit this.

[0054] In an optional embodiment, the terminal device performs combustion chamber simulation calculations based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters, which may include: performing combustion chamber simulation calculations based on each group of model parameter subsets to obtain simulation values ​​of multiple combustion chamber performance parameters associated with each model parameter subset.

[0055] Among them, the simulation result data set of multiple combustion chamber performance parameters can be expressed as f j =[f j1 ,f j2 ,…,f jp ] T , where j=1,2,…,n, and n is the total number of multiple combustion chamber performance parameters.

[0056] In step S103, the terminal device constructs a target quantity proxy model of each combustion chamber performance parameter with respect to the multiple model parameters based on the sample model parameter set and the simulation result data set.

[0057] In an optional embodiment, if Figure 2 As shown, the process of constructing a target amount proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters by the terminal device based on the sample model parameter set and the simulation result data set may include:

[0058] Step S201, for each combustion chamber performance parameter, the sample model parameter set and the first simulation value of the combustion chamber performance parameter in the simulation result data set are processed based on the active subspace method to determine the low-dimensional subspace direction associated with the combustion chamber performance parameter.

[0059] The process in which the terminal device processes the sample model parameter set and the first simulation value of the combustion chamber performance parameter in the simulation result data set based on the active subspace method to obtain a low-dimensional parameter sample set associated with the combustion chamber performance parameter may include: constructing the gradient of the combustion performance parameter with respect to the model parameter using an approximate method to obtain a covariance matrix of the gradient, wherein the covariance matrix is:

[0060]

[0061] In formula 2, is the gradient of the combustion performance parameters with respect to the model parameters, and ρ(x) is the joint probability density function of the model parameters.

[0062] Furthermore, based on the Jacobi iteration method, the eigenvalue and eigenvector matrices of the moment covariance matrix are solved, then C = WΛW T , where W is the eigenvector matrix, Λ is the diagonal matrix composed of eigenvalues, and in the eigenvalue matrix, λ1, λ2, …, λ m Arrange in descending order from large to small, m represents the data dimension; among them, if the rth eigenvalue in the eigenvalue matrix is ​​much larger than the r+1th eigenvalue, the space expanded by the first r eigenvectors in the eigenvector matrix is ​​determined as the direction of the low-dimensional subspace.

[0063] It can be understood that when the rth eigenvalue in the eigenvalue matrix is ​​much larger than the r+1th eigenvalue, the eigenvalue matrix is Eigenvector matrix in,

[0064] It should be noted that in the embodiment of the present disclosure, the active variable associated with the combustion chamber performance parameter is w1 T x=w 1,1 x1+w 1,2 x2+…+w 1,i x i , where i=1, 2,…, m.

[0065] The low-dimensional response surface model is:

[0066]

[0067] In formula 3, X is the active variable, X = w1 T x, is the combustion chamber performance parameter, f(X) is the basis function of the regression part, β is the regression coefficient vector, and z(X) is the error of random distribution.

[0068] Step S202: Projecting a plurality of model parameters in the sample model parameter set in the direction of the low-dimensional subspace to obtain active variables associated with the combustion chamber performance parameters.

[0069] In the disclosed embodiment, the active variable is composed of active direction vector components of the plurality of model parameters, wherein the linear model of the combustion chamber performance parameter with respect to the active variable is:

[0070] f(w1 T x)=a(w1 T x)+b; (Formula 6)

[0071] Step S203: determining a candidate target quantity proxy model of the combustion chamber performance parameter with respect to the plurality of model parameters according to the active variables associated with the combustion chamber performance parameter and the low-dimensional response surface model.

[0072] In the embodiment of the present disclosure, the low-dimensional response surface model is an initial relationship model of the combustion chamber performance parameters with respect to active variables determined based on the Kriging interpolation method, and the low-dimensional response surface model includes a regression part and a random part.

[0073] Among them, the low-dimensional response surface model satisfies:

[0074] E(z i (x)) = 0; (Formula 4)

[0075]

[0076] Cov[z(x i ),z(x j )]=δ 2 R[x i ,x j ,θ](1≤i,j≤n); (Formula 6)

[0077] In Formula 4 to Formula 6, E is the expectation, Var is the variance, Cov is the covariance, and R[x i ,x j ,θ] is the correlation function, which can be a Gaussian function, z(xi ) is the random distribution error of multiple model parameters associated with the i-th combustion chamber performance parameter among the multiple combustion chamber performance parameters, z(x j ) is a randomly distributed error of multiple model parameters associated with the j-th combustion chamber performance parameter among the multiple combustion chamber performance parameters.

[0078] In an optional embodiment, the process of determining the candidate target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters by the terminal device according to the active variables associated with the combustion chamber performance parameter and the low-dimensional response surface model may include: when it is determined that the low-dimensional subspace associated with the combustion chamber performance parameter is a one-dimensional subspace and the combustion chamber performance parameter is linearly distributed in the active direction, updating the low-dimensional response surface model to a linear model of the combustion chamber performance parameter with respect to the active variables; further, substituting the active variables associated with the combustion chamber performance parameter into the linear model to obtain the candidate target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters. When the low-dimensional subspace is a one-dimensional subspace and the combustion chamber performance parameter is linearly distributed in the active direction, the low-dimensional response surface model may be further simplified to reduce the complexity of the determined candidate target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters, thereby further improving the optimization efficiency of the combustion chamber simulation model parameters.

[0079] It can be understood that the terminal device substitutes the active variable associated with the combustion chamber performance parameter into the linear model, and the obtained candidate target amount proxy model of the combustion chamber performance parameter with respect to the multiple model parameters is:

[0080] f(x)=a(w 1,1 x1+w 1,2 x2+…+w 1,i x i )+b; (Formula 7)

[0081] It should be noted that in the embodiments of the present disclosure, when it is determined that the low-dimensional subspace associated with the combustion chamber performance parameters is a non-one-dimensional subspace, or when the combustion chamber performance parameters are nonlinearly distributed in the active direction, the active variables associated with the combustion chamber performance parameters can be substituted into the low-dimensional response surface model to obtain a candidate target quantity proxy model of the combustion chamber performance parameters with respect to the multiple model parameters.

[0082] Step S204: If it is determined that the candidate target quantity proxy model meets the model accuracy requirement, the candidate target quantity proxy model is determined as the target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters.

[0083] In the embodiments of the present disclosure, the sample model parameter set and the simulation result data set can be processed based on the active subspace method to reduce the sample model parameter set, thereby reducing the amount of data processing in the target quantity proxy model modeling process and improving the efficiency of determining the optimal parameter solution set for multiple model parameters; at the same time, the low-dimensional parameter sample set determined based on the active subspace method has the same reliability as the sample model parameter set before dimensionality reduction, thereby ensuring the reliability of the established target quantity proxy model.

[0084] In an optional embodiment, the process of determining whether the candidate target quantity proxy model meets the model accuracy requirement by the terminal device may include: inputting each group of model parameter subsets in the sample model parameter set into the candidate target quantity proxy model to obtain the predicted value of the combustion chamber performance parameter associated with each group of model parameter subsets; and, in the simulation result data set, reading the simulation value of the combustion chamber performance parameter associated with each group of model parameter subsets; further, determining the model accuracy index value of the candidate target quantity proxy model according to the predicted value and simulation value of the combustion chamber performance parameter respectively associated with multiple groups of model parameter subsets; wherein, if the model accuracy index value is less than the model accuracy index value threshold, it is determined that the candidate target quantity proxy model meets the model accuracy requirement. The candidate target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters can be tested for accuracy through the sample model parameter set, and when the accuracy requirement is met, the candidate target quantity proxy model is determined as the target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters, so as to further ensure the reliability of the constructed target quantity proxy model.

[0085] If the model accuracy index value is greater than or equal to the model accuracy index value threshold, the sample model parameter set is re-determined to obtain an updated sample model parameter set, and the above steps S102 to S103 are repeated using the updated sample model parameter set until a target quantity proxy model of each combustion chamber performance parameter with respect to the multiple model parameters is obtained.

[0086] Among them, the model accuracy index can be the mean absolute error (MAE), error proportion (MAE / average value), root mean square error (RMSE) or correlation coefficient, etc.; the model accuracy index value threshold can be determined based on actual needs, and the embodiments of the present disclosure do not limit this.

[0087] In an optional embodiment, for each combustion chamber performance parameter, after obtaining the active variables associated with the combustion chamber performance parameter, the terminal device may also: determine the sensitivity analysis results of the combustion chamber performance parameter to each model parameter based on the sensitivity analysis strategy and the active direction vector component of each model parameter in the active variables associated with the combustion chamber performance parameter. After obtaining the active variables associated with the combustion chamber performance parameter, the sensitivity of the combustion chamber performance parameter to each model parameter may be analyzed, so that in the process of determining the optimal parameter solution set of multiple model parameters, the Pareto optimal parameter solution set initially obtained after optimizing the mathematical model of the multi-objective optimization problem may be screened for a second time according to the sensitivity analysis results, so as to further improve the reliability of the optimal parameter solution set of multiple model parameters.

[0088] Among them, the sensitivity analysis strategy can include, the active direction vector component w 1,i The magnitude of represents the sensitivity of the combustion chamber performance parameters to the i-th model parameter among multiple model parameters, and the active direction vector component w 1,i The positive or negative value of can predict the optimization direction of the parameters. Among them, the larger the component value of the active direction vector component, the greater the influence of the i-th model parameter on the combustion chamber performance parameters. On the contrary, the smaller the component value of the active direction vector component, the smaller the influence of the i-th model parameter on the combustion chamber performance parameters. The positive value of the active direction vector component indicates that the positive disturbance of the input model parameter will lead to an increase in the simulation value of the combustion chamber performance parameter. On the contrary, the negative value of the active direction vector component indicates that the positive disturbance of the input model parameter will lead to a decrease in the simulation value of the combustion chamber performance parameter.

[0089] Then, the terminal device determines the sensitivity analysis result of the combustion chamber performance parameter to each model parameter based on the sensitivity analysis strategy and the active direction vector component of each model parameter in the active variables associated with the combustion chamber performance parameter, and the process may include: for each model parameter, if the component value of the active direction vector component of the model parameter is greater than the component value threshold, then it is determined that the influence of the model parameter on the combustion chamber performance parameter is high; or, if the component value of the active direction vector component of the model parameter is less than or equal to the component value threshold, then it is determined that the influence of the model parameter on the combustion chamber performance parameter is low; and, If the component value of the quantity is positive and the characteristic of the combustion chamber performance parameter is the higher the better, the adjustment direction of the model parameter is determined as: increase; or, the component value of the active direction vector component of the model parameter is positive and the characteristic of the combustion chamber performance parameter is the smaller the better, the adjustment direction of the model parameter is determined as: decrease; or, the component value of the active direction vector component of the model parameter is negative and the characteristic of the combustion chamber performance parameter is the higher the better, the adjustment direction of the model parameter is determined as: decrease; or, the component value of the active direction vector component of the model parameter is negative and the characteristic of the combustion chamber performance parameter is the smaller the better, the adjustment direction of the model parameter is determined as: increase.

[0090] It can be understood that the sensitivity analysis results of the combustion chamber performance parameters to each model parameter include: information on the degree of influence of each model parameter on the combustion chamber performance parameters, and adjustment direction information of each model parameter, wherein the influence degree information can be: high or low, and the adjustment direction information can be: increase or decrease.

[0091] In step S104, the terminal device constructs a mathematical model of a multi-objective optimization problem based on target quantity proxy models of the multiple model parameters and constraint conditions of the multiple combustion chamber performance parameters, and uses an optimization algorithm to perform parameter optimization to obtain an optimal parameter solution set of the multiple model parameters.

[0092] In the embodiments of the present disclosure, in order to improve the reliability of the optimal parameter solution set of the determined multiple model parameters, the mathematical model of the multi-objective optimization problem includes not only multiple combustion chamber performance parameters, but also target quantity proxy models of the multiple model parameters, and constraints, wherein the constraints include the initial parameter ranges of the multiple model parameters and the combustion chamber performance parameter thresholds of each combustion chamber performance parameter among the multiple combustion chamber performance parameters, so as to evaluate the parameter ranges of the multiple model parameters obtained after the optimization of the mathematical model of the multi-objective optimization problem in combination with the evaluation index of the combustion chamber performance parameters (i.e., the combustion chamber performance parameter thresholds).

[0093] In an optional embodiment, if Figure 3As shown, the terminal device constructs a multi-objective optimization problem mathematical model based on target quantity proxy models of the plurality of model parameters respectively for the plurality of combustion chamber performance parameters, and constraint conditions, and uses an optimization algorithm to perform parameter optimization. The process of obtaining the optimal parameter solution set of the plurality of model parameters may include:

[0094] Step S301, constructing a mathematical model of a multi-objective optimization problem based on target quantity proxy models of multiple combustion chamber performance parameters respectively related to multiple model parameters and constraint conditions.

[0095] Among them, the mathematical model of the multi-objective optimization problem is:

[0096]

[0097] In Formula 8, f j (x) is a relationship model of the j-th combustion chamber performance parameter among the multiple combustion chamber performance parameters with respect to the multiple model parameters, i (L) is the minimum value of the i-th model parameter among the m model parameters, x i U is the maximum value of the i-th model parameter among the m model parameters; f j (x) (L) is the minimum threshold value of the jth combustion chamber performance parameter among the n combustion chamber performance parameters, and f j (x) (U) is the maximum threshold of the j-th combustion chamber performance parameter among the n combustion chamber performance parameters.

[0098] Step S302: optimizing the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain a Pareto optimal parameter solution set of multiple model parameters.

[0099] In the embodiment of the present disclosure, the terminal device optimizes the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain the Pareto optimal parameter solution set of multiple model parameters. The selected genetic algorithm can be determined based on actual needs, and the embodiment of the present disclosure does not limit this.

[0100] In an optional implementation, the terminal device may determine the Pareto optimal parameter solution set of multiple model parameters based on a non-dominated sorting genetic algorithm III (NSGA-III), wherein the terminal device optimizes the mathematical model of the multi-objective optimization problem based on the NSGA-III algorithm, and the process of obtaining the Pareto optimal parameter solution set of multiple model parameters may include: performing non-dominated sorting on individuals in an initial population consisting of initial parameter ranges of multiple target parameters to obtain multiple non-dominated layers, and creating a population reference point; then, solving the minimum value of each dimension of the target of the individuals in the current population to form an ideal point of the current population, and moving the origin of the solution space to the ideal point, and solving the ASF equation to find the extreme point:

[0101]

[0102] In formula 9, is the extreme point, is the unit direction vector of the coordinate axis.

[0103] Furthermore, a hyperplane containing the extreme points and the ideal point (origin) of each target direction is constructed, the intercept between the hyperplane and the coordinate axis is obtained, and the target quantity is normalized; and the Euclidean distance between the reference point and the individual is calculated, all individuals are associated with the reference point, individuals are extracted from the non-dominated layer and added to the next generation population, and the above process is repeated until the convergence condition is reached.

[0104] Among them, the population reference points are created using the reference point generation method proposed by Deb and Jain. The reference points include two layers of reference points, the boundary layer and the inner layer, which can ensure the wide distribution of reference points and improve the calculation efficiency.

[0105] Step S303, based on the combustion chamber simulation accuracy condition and the sensitivity analysis results of the multiple combustion chamber performance parameters to each model parameter, the Pareto optimal parameter solution set of the multiple model parameters is secondary screened to obtain the secondary optimal parameter solution set of the multiple model parameters.

[0106] In an optional embodiment, the terminal device performs secondary screening on the Pareto optimal parameter solution set of the multiple model parameters according to the combustion chamber simulation accuracy condition and the sensitivity analysis results of the multiple combustion chamber performance parameters to each model parameter respectively, and the process of obtaining the secondary optimal parameter solution set of the multiple model parameters may include: sampling in the Pareto optimal parameter solution set of the multiple model parameters to obtain the model parameter set to be verified, then, performing simulation calculation of the combustion chamber based on each group of model parameter subsets to be verified in the model parameter set to be verified, and obtaining the simulation values ​​to be verified of the multiple combustion chamber performance parameters associated with each group of model parameter subsets to be verified; at the same time, in the Pareto optimal parameter solution set of the multiple model parameters, deleting the sampling values ​​to be verified contained in the target model parameter subset to be verified, and obtaining the initial secondary optimal parameter solution set of the multiple model parameters; further, based on the adjustment direction information in the sensitivity analysis results of each combustion chamber performance parameter to each model parameter, in the initial secondary optimal parameter solution set of the multiple model parameters, the initial secondary optimal parameter solution of each model parameter is increased or decreased, and the secondary optimal parameter solution set of the multiple model parameters is obtained.

[0107] Among them, the model parameter set to be verified includes multiple sampled values ​​of model parameters to be verified, and among the multiple simulation values ​​of combustion chamber performance parameters to be verified associated with the target model parameter subset to be verified, there is at least one simulation value of combustion chamber performance parameter to be verified that does not meet the combustion chamber performance parameter threshold; wherein, the simulation value of the combustion chamber performance parameter to be verified, meeting the combustion chamber performance parameter threshold means that the simulation value of the combustion chamber performance parameter to be verified is greater than the combustion chamber performance parameter threshold, or the simulation value of the combustion chamber performance parameter to be verified is less than or equal to the combustion chamber performance parameter threshold, wherein the combustion chamber performance parameter threshold, and the degree of increase or decrease of the initial quadratic optimal parameter solution of each model parameter, can be determined based on actual needs, and the embodiments of the present disclosure are not limited to this.

[0108] Step S304, using the secondary optimal parameter solution set of the plurality of model parameters to perform simulation calculation of the combustion chamber, to obtain second simulation values ​​of the plurality of combustion chamber performance parameters.

[0109] In an optional embodiment, the terminal device uses the secondary optimal parameter solution set of the multiple model parameters to perform simulation calculations on the combustion chamber to obtain the second simulation values ​​of the multiple combustion chamber performance parameters, which may include: sampling in the secondary optimal parameter solution set of the multiple model parameters to obtain a subset of model parameters to be simulated, and then using the subset of model parameters to be simulated to perform simulation calculations on the combustion chamber to obtain the second simulation values ​​of the multiple combustion chamber performance parameters. The subset of model parameters to be simulated includes the sampled values ​​to be verified of the multiple model parameters.

[0110] Step S305: if the second simulation values ​​of the plurality of combustion chamber performance parameters respectively satisfy each combustion chamber performance parameter threshold, the secondary optimal parameter solution set of the plurality of model parameters is determined as the optimal parameter solution set of the plurality of model parameters.

[0111] In the disclosed embodiment, after optimizing the mathematical model of the multi-objective optimization problem and obtaining the Pareto optimal parameter solution set of multiple model parameters, the Pareto optimal parameter solution set of the multiple model parameters is subjected to a secondary screening to improve the reliability of the optimal parameter solution set of the multiple model parameters finally determined; on the other hand, after the Pareto optimal parameter solution set of the multiple model parameters is subjected to a secondary screening, based on the accuracy requirements of the combustion chamber performance parameters in the simulation calculation process of the combustion chamber, the Pareto optimal parameter solution set of the multiple model parameters after the secondary screening is evaluated to finally determine the optimal parameter solution set of the multiple model parameters. This can improve the reliability of the determined optimal parameter solution set of the multiple model parameters and ensure the accuracy of the simulation results obtained in the simulation calculation process of the combustion chamber based on the optimal parameter solution set of the multiple model parameters.

[0112] In an optional embodiment, the terminal device determines whether the second simulation values ​​of multiple combustion chamber performance parameters respectively meet each combustion chamber performance parameter threshold, including: for each combustion chamber performance parameter, the second simulation value of the combustion chamber performance parameter is greater than the combustion chamber performance parameter threshold, or the second simulation value of the combustion chamber performance parameter is less than or equal to the combustion chamber performance parameter threshold.

[0113] In an optional embodiment, if the second simulation value of at least one combustion chamber performance parameter among multiple combustion chamber performance parameters does not meet the corresponding combustion chamber performance parameter threshold, the subset of model parameters to be simulated is added to the sample model parameter set, and the second simulation values ​​of multiple combustion chamber performance parameters are added to the simulation result data set of multiple combustion chamber performance parameters, and the above steps S103 to S104 are repeated until the optimal parameter solution set of multiple model parameters is obtained.

[0114] In an optional embodiment, the terminal device uses an optimization algorithm to perform parameter optimization, and the process of obtaining the optimal parameter solution set of the multiple model parameters may include: optimizing the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain the Pareto optimal parameter solution set of the multiple model parameters; and performing secondary screening on the Pareto optimal parameter solution set of the multiple model parameters according to the combustion chamber simulation accuracy conditions and the sensitivity analysis results of each model parameter of multiple combustion chamber performance parameters to obtain the optimal parameter solution set of the multiple model parameters; the data processing flow in the process of determining the optimal parameter solution set of multiple model parameters can be reduced, thereby improving the efficiency of determining the optimal parameter solution set of multiple model parameters.

[0115] In an optional embodiment, the terminal device uses an optimization algorithm to perform parameter optimization, and the process of obtaining the optimal parameter solution set of the multiple model parameters may include: optimizing the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain the Pareto optimal parameter solution set of the multiple model parameters; and performing secondary screening on the Pareto optimal parameter solution set of the multiple model parameters based on the sensitivity analysis results of each model parameter of multiple combustion chamber performance parameters to obtain the optimal parameter solution set of the multiple model parameters; the processing flow in the process of determining the optimal parameter solution set of multiple model parameters can be further reduced, and the efficiency of determining the optimal parameter solution set of multiple model parameters can be further improved.

[0116] For example, Figure 4 As shown, Figure 4 A flow chart of a combustion chamber simulation model parameter optimization method provided by an embodiment of the present disclosure is shown, comprising:

[0117] Step S401 : determining a sample model parameter set according to initial parameter ranges of a plurality of model parameters of a plurality of combustion chamber simulation models.

[0118] Step S402: performing combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters.

[0119] Step S403, for each combustion chamber performance parameter, the sample model parameter set and the first simulation value of the combustion chamber performance parameter in the simulation result data set are processed based on the active subspace method to determine the low-dimensional subspace direction associated with the combustion chamber performance parameter.

[0120] Step S404: Projecting the plurality of model parameters in the sample model parameter set in the direction of the low-dimensional subspace to obtain active variables associated with the combustion chamber performance parameters.

[0121] Step S405 , determining a candidate target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters based on the active variables associated with the combustion chamber performance parameter and the low-dimensional response surface model.

[0122] Step S406, determining whether the candidate target quantity proxy model meets the model accuracy requirement.

[0123] Step S407: If it is determined that the candidate target quantity proxy model does not meet the model accuracy requirements, the sample model parameter set is re-determined to obtain an updated sample model parameter set, and the above process is repeated starting from step S402 using the updated sample model parameter set until the candidate target quantity proxy model meets the model accuracy requirements.

[0124] Step S408: If it is determined that the candidate target quantity proxy model meets the model accuracy requirement, the candidate target quantity proxy model is determined as the target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters.

[0125] Step S409, constructing a mathematical model of a multi-objective optimization problem based on target quantity proxy models of the plurality of combustion chamber performance parameters respectively related to the plurality of model parameters and constraint conditions.

[0126] Step S410, optimizing the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain a Pareto optimal parameter solution set of multiple model parameters.

[0127] Step S411, based on the combustion chamber simulation accuracy condition and the sensitivity analysis results of the multiple combustion chamber performance parameters to each model parameter, the Pareto optimal parameter solution set of the multiple model parameters is secondary screened to obtain the secondary optimal parameter solution set of the multiple model parameters.

[0128] Step S412, using the secondary optimal parameter solution set of multiple model parameters to perform simulation calculation of the combustion chamber to obtain second simulation values ​​of the multiple combustion chamber performance parameters.

[0129] Step S413, determining whether the second simulation values ​​of the plurality of combustion chamber performance parameters respectively meet each combustion chamber performance parameter threshold.

[0130] Step S414: if the second simulation value of at least one combustion chamber performance parameter among the multiple combustion chamber performance parameters does not meet the corresponding combustion chamber performance parameter threshold, then the subset of model parameters to be simulated is added to the sample model parameter set, and the second simulation values ​​of the multiple combustion chamber performance parameters are added to the simulation result data set of the multiple combustion chamber performance parameters, and the above steps are repeated starting from step S403 until the optimal parameter solution set of the multiple model parameters is obtained.

[0131] Step S415: if the second simulation values ​​of the plurality of combustion chamber performance parameters respectively satisfy each combustion chamber performance parameter threshold, the secondary optimal parameter solution set of the plurality of model parameters is determined as the optimal parameter solution set of the plurality of model parameters.

[0132] like Figure 5 As shown, Figure 5FIG10 is a diagram showing the optimal parameter solution set of multiple model parameters of multiple combustion chamber simulation models (atomization model, evaporation model, turbulence model and combustion model) determined by using the combustion chamber simulation model parameter optimization method provided by the embodiment of the present disclosure, and the schematic diagram of the distribution of the combustion chamber outlet temperature during the combustion chamber simulation calculation process, and FIG10 is a diagram showing the optimal parameter solution set of multiple model parameters of multiple combustion chamber simulation models (atomization model, evaporation model, turbulence model and combustion model) determined by using the combustion chamber simulation model parameter optimization method provided by the related technology, and the schematic diagram of the distribution of the combustion chamber outlet temperature during the combustion chamber simulation calculation process (such as ... Figure 6 The distribution accuracy of the combustion chamber outlet temperature is improved by 5% to 10% compared to the conventional combustion chamber outlet temperature.

[0133] An exemplary embodiment of the present disclosure provides a combustion chamber simulation model parameter optimization device, which may be a chip of a terminal device. Figure 7 FIG. 1 shows a schematic block diagram of the functional modules of a combustion chamber simulation model parameter optimization device according to an exemplary embodiment of the present disclosure. Figure 7 As shown, the combustion chamber simulation model parameter optimization device 700 includes:

[0134] A first determination module 701 is configured to determine a sample model parameter set according to initial parameter ranges of multiple model parameters of multiple combustion chamber simulation models;

[0135] A simulation module 702 is configured to perform combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters;

[0136] A construction module 703 is configured to construct a target amount proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters based on the sample model parameter set and the simulation result data set;

[0137] The second determination module 704 is configured to construct a mathematical model of a multi-objective optimization problem based on target quantity proxy models of the plurality of combustion chamber performance parameters respectively related to the plurality of model parameters, and constraint conditions, and use an optimization algorithm to perform parameter optimization to obtain an optimal parameter solution set for the plurality of model parameters.

[0138] Optionally, the first determining module 701 is configured to:

[0139] Normalizing the initial parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models to obtain normalized parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models;

[0140] The optimal Latin hypercube sampling is repeatedly performed in the normalized parameter range of multiple model parameters of multiple combustion chamber simulation models to obtain a candidate model parameter set, and the system potential energy of the candidate model parameter set is determined based on the AE potential energy criterion. Among the candidate model parameter sets obtained by multiple samplings, the candidate model parameter set with the smallest system potential energy is determined as the sample model parameter set.

[0141] Optionally, the construction module 703 is configured to:

[0142] For each combustion chamber performance parameter, processing the sample model parameter set and a first simulation value of the combustion chamber performance parameter in the simulation result data set based on an active subspace method to determine a low-dimensional subspace direction associated with the combustion chamber performance parameter;

[0143] Projecting a plurality of model parameters in the sample model parameter set in the direction of the low-dimensional subspace to obtain active variables associated with the combustion chamber performance parameters, wherein the active variables are composed of active direction vector components of the plurality of model parameters;

[0144] Determining a candidate target quantity proxy model of the combustion chamber performance parameter with respect to the plurality of model parameters according to the active variables associated with the combustion chamber performance parameter and a low-dimensional response surface model, wherein the low-dimensional response surface model is an initial relationship model of the combustion chamber performance parameter with respect to the active variables determined based on a Kriging interpolation method;

[0145] If it is determined that the candidate target quantity proxy model meets the model accuracy requirement, the candidate target quantity proxy model is determined as the target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters.

[0146] Optionally, the construction module 703 is configured to:

[0147] When it is determined that the low-dimensional subspace associated with the combustion chamber performance parameter is a one-dimensional subspace and the combustion chamber performance parameter is linearly distributed in the active direction, updating the low-dimensional response surface model to a linear model of the combustion chamber performance parameter with respect to the active variable;

[0148] Substituting active variables associated with the combustion chamber performance parameters into the linear model, a target quantity proxy model of the combustion chamber performance parameters with respect to the plurality of model parameters is obtained.

[0149] Optionally, the construction module 703 is further configured to:

[0150] Inputting each group of model parameter subsets in the sample model parameter set into the target quantity proxy model respectively to obtain a predicted value of a combustion chamber performance parameter associated with each group of model parameter subsets, wherein each group of model parameter subsets includes sampled values ​​of multiple model parameters;

[0151] In the simulation result data set, reading the simulation value of the combustion chamber performance parameter associated with each group of model parameter subsets;

[0152] Determining a model accuracy index value of the candidate target quantity proxy model according to the predicted values ​​and simulated values ​​of the combustion chamber performance parameters respectively associated with the plurality of groups of model parameter subsets;

[0153] If the model accuracy index value is less than the model accuracy index value threshold, it is determined that the candidate target quantity proxy model meets the model accuracy requirement.

[0154] Optionally, the construction module 703 is configured to:

[0155] Based on the sensitivity analysis strategy and the active direction vector component of each model parameter in the active variables associated with the combustion chamber performance parameter, a sensitivity analysis result of the combustion chamber performance parameter to each model parameter is determined.

[0156] Optionally, the second determining module 704 is configured to:

[0157] Constructing a mathematical model of a multi-objective optimization problem based on target quantity proxy models of multiple combustion chamber performance parameters respectively related to multiple model parameters and constraint conditions;

[0158] Optimizing the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain a Pareto optimal parameter solution set of multiple model parameters;

[0159] According to the combustion chamber simulation accuracy condition and the sensitivity analysis results of the multiple combustion chamber performance parameters on each model parameter, the Pareto optimal parameter solution set of the multiple model parameters is secondary screened to obtain the secondary optimal parameter solution set of the multiple model parameters;

[0160] Performing simulation calculation of the combustion chamber using the secondary optimal parameter solution set of the plurality of model parameters to obtain second simulation values ​​of the plurality of combustion chamber performance parameters;

[0161] If the second simulation values ​​of the plurality of combustion chamber performance parameters respectively satisfy each combustion chamber performance parameter threshold, the secondary optimal parameter solution set of the plurality of model parameters is determined as the optimal parameter solution set of the plurality of model parameters.

[0162] The exemplary embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to cause the electronic device to perform the method according to the embodiment of the present disclosure when executed by the at least one processor.

[0163] The exemplary embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform the method according to the embodiments of the present disclosure.

[0164] like Figure 8 As shown, the exemplary embodiment of the present disclosure further provides a computer program product 800, including a computer program 801, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to perform the method according to the embodiment of the present disclosure.

[0165] refer to Fig. 9 , a block diagram of an electronic device 900 that can be used as a terminal device of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0166] like Fig. 9 As shown, the electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0167] A plurality of components in the electronic device 900 are connected to the I / O interface 905, including: an input unit 906, an output unit 907, a storage unit 908, and a communication unit 909. The input unit 906 may be any type of device capable of inputting information to the electronic device 900, and the input unit 906 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 907 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 908 may include, but is not limited to, a disk, an optical disk. The communication unit 909 allows the electronic device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0168] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above. For example, in some embodiments, the method of the exemplary embodiment of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 900 via the ROM 902 and / or the communication unit 909. In some embodiments, the computing unit 901 may be configured to perform the method of the exemplary embodiment of the present disclosure by any other appropriate means (e.g., by means of firmware).

[0169] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0170] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0173] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0174] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0175] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device or other programmable device. The computer program or instruction may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instruction may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium may be a magnetic medium, for example, a floppy disk, a hard disk, a tape; it may also be an optical medium, for example, a digital video disc (DVD); it may also be a semiconductor medium, for example, a solid state drive (SSD).

[0176] Although the present disclosure has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely exemplary illustrations of the present disclosure as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A method for optimizing parameters of a combustion chamber simulation model, characterized in that: include: Determining a sample model parameter set according to initial parameter ranges of multiple model parameters of multiple combustion chamber simulation models; Performing combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters; Based on the sample model parameter set and the simulation result data set, constructing a target quantity proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters; A mathematical model of a multi-objective optimization problem is constructed based on target quantity proxy models of multiple combustion chamber performance parameters respectively related to the multiple model parameters, and constraint conditions, and an optimization algorithm is used to perform parameter optimization to obtain an optimal parameter solution set for the multiple model parameters.

2. The combustion chamber simulation model parameter optimization method according to claim 1, characterized in that: The step of determining a sample model parameter set according to initial parameter ranges of a plurality of model parameters of a plurality of combustion chamber simulation models comprises: Normalizing the initial parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models to obtain normalized parameter ranges of the multiple model parameters of the multiple combustion chamber simulation models; The optimal Latin hypercube sampling is repeatedly performed in the normalized parameter range of multiple model parameters of multiple combustion chamber simulation models to obtain a candidate model parameter set, and the system potential energy of the candidate model parameter set is determined based on the AE potential energy criterion. Among the candidate model parameter sets obtained by multiple samplings, the candidate model parameter set with the smallest system potential energy is determined as the sample model parameter set.

3. The combustion chamber simulation model parameter optimization method according to claim 1, characterized in that: The step of constructing a target amount proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters based on the sample model parameter set and the simulation result data set includes: For each combustion chamber performance parameter, processing the sample model parameter set and a first simulation value of the combustion chamber performance parameter in the simulation result data set based on an active subspace method to determine a low-dimensional subspace direction associated with the combustion chamber performance parameter; Projecting a plurality of model parameters in the sample model parameter set in the direction of the low-dimensional subspace to obtain active variables associated with the combustion chamber performance parameters, wherein the active variables are composed of active direction vector components of the plurality of model parameters; Determining a candidate target quantity proxy model of the combustion chamber performance parameter with respect to the plurality of model parameters according to the active variables associated with the combustion chamber performance parameter and a low-dimensional response surface model, wherein the low-dimensional response surface model is an initial relationship model of the combustion chamber performance parameter with respect to the active variables determined based on a Kriging interpolation method; If it is determined that the candidate target quantity proxy model meets the model accuracy requirement, the candidate target quantity proxy model is determined as the target quantity proxy model of the combustion chamber performance parameter with respect to the multiple model parameters.

4. The combustion chamber simulation model parameter optimization method according to claim 3, characterized in that: The step of determining a candidate target quantity proxy model of the combustion chamber performance parameter with respect to the plurality of model parameters based on the active variables associated with the combustion chamber performance parameter and the low-dimensional response surface model comprises: When it is determined that the low-dimensional subspace associated with the combustion chamber performance parameter is a one-dimensional subspace and the combustion chamber performance parameter is linearly distributed in the active direction, updating the low-dimensional response surface model to a linear model of the combustion chamber performance parameter with respect to the active variable; The active variables associated with the combustion chamber performance parameters are substituted into the linear model to obtain a candidate target quantity proxy model of the combustion chamber performance parameters with respect to the plurality of model parameters.

5. The combustion chamber simulation model parameter optimization method according to claim 3, characterized in that: Determining whether the candidate target quantity proxy model meets the model accuracy requirement includes: Inputting each group of model parameter subsets in the sample model parameter set into the candidate target quantity proxy model respectively to obtain a predicted value of a combustion chamber performance parameter associated with each group of model parameter subsets, wherein each group of model parameter subsets includes sampled values ​​of multiple model parameters; In the simulation result data set, reading the simulation value of the combustion chamber performance parameter associated with each group of model parameter subsets; Determining a model accuracy index value of the candidate target quantity proxy model according to the predicted values ​​and simulated values ​​of the combustion chamber performance parameters respectively associated with the plurality of groups of model parameter subsets; If the model accuracy index value is less than the model accuracy index value threshold, it is determined that the candidate target quantity proxy model meets the model accuracy requirement.

6. The combustion chamber simulation model parameter optimization method according to claim 3, characterized in that: The method further comprises: Based on the sensitivity analysis strategy and the active direction vector component of each model parameter in the active variables associated with the combustion chamber performance parameter, a sensitivity analysis result of the combustion chamber performance parameter to each model parameter is determined.

7. The combustion chamber simulation model parameter optimization method according to claim 6, characterized in that: Based on the target quantity proxy models of the plurality of combustion chamber performance parameters respectively related to the plurality of model parameters, and the constraint conditions, a mathematical model of a multi-objective optimization problem is constructed, and an optimization algorithm is used to perform parameter optimization to obtain an optimal parameter solution set of the plurality of model parameters, including: Constructing a mathematical model of a multi-objective optimization problem based on target quantity proxy models of multiple combustion chamber performance parameters respectively related to multiple model parameters and constraint conditions; Optimizing the mathematical model of the multi-objective optimization problem based on a genetic algorithm to obtain a Pareto optimal parameter solution set of multiple model parameters; According to the combustion chamber simulation accuracy condition and the sensitivity analysis results of the multiple combustion chamber performance parameters on each model parameter, the Pareto optimal parameter solution set of the multiple model parameters is secondary screened to obtain the secondary optimal parameter solution set of the multiple model parameters; Performing simulation calculation of the combustion chamber using the secondary optimal parameter solution set of the plurality of model parameters to obtain second simulation values ​​of the plurality of combustion chamber performance parameters; If the second simulation values ​​of the plurality of combustion chamber performance parameters respectively satisfy each combustion chamber performance parameter threshold, the secondary optimal parameter solution set of the plurality of model parameters is determined as the optimal parameter solution set of the plurality of model parameters.

8. A combustion chamber simulation model parameter optimization device, characterized in that: include: a determination module configured to determine a sample model parameter set according to initial parameter ranges of a plurality of model parameters of a plurality of combustion chamber simulation models; A simulation module is configured to perform combustion chamber simulation calculation based on the sample model parameter set to obtain a simulation result data set of multiple combustion chamber performance parameters; A construction module configured to construct a target amount proxy model of each combustion chamber performance parameter with respect to the plurality of model parameters based on the sample model parameter set and the simulation result data set; The determination module is configured to construct a mathematical model of a multi-objective optimization problem based on target quantity proxy models of the plurality of combustion chamber performance parameters respectively related to the plurality of model parameters, and constraint conditions, and use an optimization algorithm to perform parameter optimization to obtain an optimal parameter solution set of the plurality of model parameters.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the combustion chamber simulation model parameter optimization method described in claim 1.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the combustion chamber simulation model parameter optimization method described in claim 1 is implemented.

Images