A power plant cooling system mixed variable optimization design method and system and a storage medium

Abstract

The application discloses a kind of power device cooling system mixed variable optimization design method, system and storage medium, by the different processing mode of mapping ordered category type variable to one-dimensional hidden space, unordered category type variable is mapped to high-dimensional hidden space, the essential characteristics of different category type variable is completely retained, so that model can accurately depict the coupling mechanism of numerical-category mixed variable, significantly improve the fitting precision and generalization ability of model, accurately reflect the comprehensive influence of different variable combination on the acoustic performance of cooling system, provide reliable model basis for subsequent optimization.The application takes total sound pressure level response as the core optimization design target, realizes the efficient optimization design of power device cooling system containing mixed variable through the whole process of parameterized acoustic analysis, hidden space Gaussian process model training and iterative optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power device cooling system optimization, in particular to a power device cooling system mixed variable optimization design method, system and storage medium. BACKGROUND

[0002] As a key auxiliary system of core power equipment such as engines and motors, the design rationality of the power device cooling system directly affects the noise control level of the power device. In actual engineering scenarios, the design of the cooling system needs to consider both numerical design variables (such as air duct structure size, fan configuration, etc.) and categorical design variables (such as cooling medium type, fan speed level, air duct layout scheme, etc.). The coupling effect of the two types of variables makes the system optimization design challenging.

[0003] Traditional cooling system optimization methods mostly focus on the optimization of a single type of variable, such as using gradient descent, genetic algorithm, etc. optimization strategies for numerical variables only, or enumerating and screening categorical variables. However, such methods do not fully consider the mixed characteristics of numerical and categorical variables, resulting in limitations in the optimization process. Ignoring the differences between variable types can lead to insufficient accuracy of the optimization model, making it difficult to accurately reflect the comprehensive influence of different variable combinations on system performance. Moreover, traditional methods such as enumeration are prone to problems such as rapid increase in computational load, low optimization efficiency, and difficulty in finding global optimal solutions when dealing with multiple categorical and numerical variable combinations. SUMMARY

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application proposes a power device cooling system mixed variable optimization design method.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present application is as follows:

[0006] A power device cooling system mixed variable optimization design method, comprising the following steps: S1, generating an input matrix containing initial training samples , with a size of ; S2, combining the input matrix formed by initial samples corresponding total sound pressure level response , forming a training sample set ; S3, mapping the label value of the ordered categorical design variable to a one-dimensional ordered coordinate point in a one-dimensional hidden space; S4, mapping the label value of the unordered categorical design variable to a multi-dimensional unordered coordinate point in a high-dimensional hidden space; S5, according to the training sample set Train the latent space Gaussian process model; S6, iterate over numerical and categorical design variables to obtain the iterated input variables. And obtain the input variables after iteration. Corresponding total sound pressure level response S7, Update sample count ,Will Merged into the training sample set ,judge Is it greater than the preset threshold N? If yes, proceed to step S8; otherwise, return to step S3. In S8, the training sample set... The numerical and categorical design variables corresponding to the minimum total sound pressure level response are used as the optimization design scheme for the power unit cooling system.

[0007] Further, step S3 specifically includes: for an ordered categorical design variable with L class values, sorting the label values ​​of the ordered categorical design variable from smallest to largest to obtain a one-dimensional variable sequence. ; Introducing inclusion An ordered sequence of coordinate points in a one-dimensional latent space To map one-to-one one-dimensional variable sequences Parametric values ​​of ordered categorical design variables in the interval; values ​​of one-dimensional latent space coordinates within the interval Inside; and , The values ​​of the remaining one-dimensional latent space coordinates satisfy .

[0008] Further, step S4 specifically includes: for an unordered categorical design variable with M category values, the sequence of label values ​​of the M unordered categorical design variables is represented as an unordered variable sequence. ; Introducing inclusion indivual A multidimensional unordered sequence of coordinate points in hidden space One-to-one mapping sequence The parameterized values ​​of unordered categorical design variables in the model, where the non-zero coordinate component values ​​at each coordinate point are... All within the range Inside.

[0009] Furthermore, in step S5, the hyperparameters of the latent space Gaussian process model that need to be determined through training include: the regression constant term. Process variance The feature scale coefficients implicit in the correlation function, and the values ​​of the one-dimensional latent space coordinates corresponding to the categories of ordered categorical design variables. The non-zero coordinate component values ​​of the high-dimensional latent space coordinate points corresponding to the category values ​​of unordered categorical design variables. .

[0010] Furthermore, the hyperparameters can be obtained as follows: by maximizing the log-likelihood function, the covariance matrix corresponding to the maximization of the log-likelihood function is obtained. The log-likelihood function is:

[0011] ; for The covariance matrix, The process variance is the number of samples. Feature scaling coefficients and the values ​​of coordinates in the one-dimensional latent space. Non-zero coordinate component values ​​of coordinate points in high-dimensional hidden space All are implicit in the covariance matrix In the middle; the regression constant term It is calculated using the following formula: ; For all elements to be 1 vector.

[0012] Furthermore, the aforementioned The Line 1 The elements of the column are:

[0013] ;

[0014] For the first Response of a sample With the Response of a sample The correlation function between them includes the feature scale coefficient and the values ​​of the coordinates of the one-dimensional latent space points. Non-zero coordinate component values ​​of coordinate points in high-dimensional hidden space .

[0015] Furthermore, the formula for the relevant function is as follows:

[0016] ;

[0017] For the first The distance components of a design variable, for numerical design variables. , For ordered categorical design variables, , For unordered categorical design variables, , ;

[0018] For the first a characteristic scale coefficient corresponding to the design variable; a total number of categories of the ordered category type design variable; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a numerical design variable value of the i-th design variable of the i-th sample; a unit vector with the i-th element being 1 and the rest of the elements being 0; a unit vector with the i-th element being 1 and the rest of the elements being 0. Further, in step S7, the input variable corresponding to the maximum of the improved expected acquisition function is obtained by maximizing the improved expected acquisition function;

[0019] .

[0020] a posterior predictive mean of the latent space Gaussian process model corresponding to the input variable ; a minimum value of the response in the training sample set , a cumulative distribution function of a standard normal distribution, a probability density function of a standard normal distribution; a posterior predictive standard deviation of the latent space Gaussian process model corresponding to the input variable .

[0021] The application also provides a power device cooling system mixed variable optimization design system, comprising: a matrix generation module for generating an input matrix containing initial training samples, wherein the size of the input matrix is ; a training sample generation module for combining ​​Input matrix formed by initial samples Corresponding total sound pressure level response , form a training sample set ; an ordered variable mapping module, used for mapping the label value of the ordered categorical design variable to a one-dimensional ordered coordinate point in a one-dimensional hidden space; an unordered variable mapping module, used for mapping the label value of the unordered categorical design variable to a multi-dimensional unordered coordinate point in a high-dimensional hidden space; a training module, used for training the hidden space Gaussian process model according to the training sample set ; an iteration module, used for iterating the numerical design variable and the categorical design variable to obtain the input variable after iteration , and obtaining the input variable after iteration Corresponding total sound pressure level response ; a loop module, used for updating the sample number , into the training sample set ; determining whether the minimum total sound pressure level response is greater than a preset threshold N; and an optimization design scheme output module, used for taking the numerical design variable and the categorical design variable corresponding to the minimum total sound pressure level response in the training sample set as the optimization design scheme of the power device cooling system.

[0022] The application further provides a storage medium, which stores a computer program, and the computer program is executed by a processor to realize the power device cooling system mixed variable optimization design method.

[0023] The application has the following beneficial effects:

[0024] ​By differentiating the processing mode of mapping ordered categorical variables to one-dimensional latent space and unordered categorical variables to high-dimensional latent space, the essential characteristics of different types of variables are completely preserved, avoiding the feature loss or unreasonable association problem caused by variable parameterization in traditional methods. The model can accurately depict the coupling mechanism of the two types of variables and accurately reflect the comprehensive influence of different variable combinations on the acoustic performance of the cooling system, significantly improving the fitting precision and generalization ability of the model, and providing a reliable model basis for subsequent optimization. The training sample set is trained by using the latent space Gaussian process model, and the mixed variables are efficiently iteratively optimized, the sample set is iteratively updated and the termination condition is dynamically judged, which effectively reduces the redundant calculation amount and avoids the problem of rapid increase of calculation amount and long optimization period in traditional methods. At the same time, the Gaussian process model has strong nonlinear fitting and prediction ability, which can quickly focus on the optimal variable combination area in the iteration process, improve the search efficiency of the global optimal solution, and ensure that the ideal optimization result is obtained efficiently within the preset threshold. The present application takes the overall sound pressure level response as the core optimization target, realizes the accurate mapping of mixed variables and acoustic performance through the whole process of parameterized model acoustic analysis, latent space model training and iterative optimization.

[0025] In addition to the purposes, features and advantages described above, the present application has other purposes, features and advantages. The present application will be described in further detail below with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0026] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application, illustrate the preferred embodiments of the application and assist in the explanation of the application. In the drawings:

[0027] Figure 1 is a flowchart of the method of the present application. DETAILED DESCRIPTION

[0028] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0029] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0030] It should be noted that all the direction indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, movement condition, etc. between components in a certain specific posture (as shown in the drawings), and if the specific posture changes, the direction indications will also change accordingly.

[0031] In addition, the descriptions involving "first", "second", etc. in the present application are only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the fact that a person skilled in the art can realize it, and when the combination of technical solutions contradicts each other or cannot be realized, it should be considered that the combination of technical solutions does not exist and is not within the protection scope required by the present application.

[0032] Please refer to Figure 1 , the present application provides a preferred embodiment of a power device cooling system mixed variable optimization design method, which comprises steps S1, S2, S3, S4, S5, S6, S7 and S8.

[0033] S1, generate an input matrix containing initial training samples , with a size of . The total number of numerical design variables is , and the total number of category design variables is

[0034] S2, combine the input matrix formed by initial samples corresponding total sound pressure level responses to form a training sample set . Generally, the total sound pressure level response can be represented by a vector to form a total sound pressure level response vector , and the total sound pressure level response vector is formed by samples corresponding to total sound pressure level responses combined to form a vector, which can also be considered as a matrix with only one column. That is, the total sound pressure level response corresponding to the first sample in the input matrix is the first element in the total sound pressure level response vector . It can be understood that the total sound pressure level values corresponding to the initial samples can be obtained by experiment, or by constructingnumerical design variables and a parametric analysis model of the power plant cooling system, to obtain simulation results. The simulation software can be ANSYS Fluent, Siemens Simcenter, or MSC Actran.

[0035] S3, mapping the label value of the ordered categorical design variable to a one-dimensional ordered coordinate point in a one-dimensional latent space.

[0036] S4, mapping the label value of the unordered categorical design variable to a multi-dimensional unordered coordinate point in a high-dimensional latent space.

[0037] S5, according to the training sample set , training the latent space Gaussian process model.

[0038] S6, iterating the numerical design variables and the categorical design variables to obtain the input variables after iteration, and obtaining the corresponding total sound pressure level response . .The total sound pressure level response can be obtained through experiments or by constructing a parametric analysis model of the power plant cooling system and performing simulation.

[0039] S7, updating the number of samples , merging into the training sample set , and determining whether it is greater than the preset threshold N: if yes, go to step S8, if no, return to step S3. In the updated , the number of rows in the size increases by 1, and the size increases by 1 row at the bottom based on the original size. For example, if the size of is 2x5, after updating and merging , the size becomes 3x5. The parameters of are supplemented to the last added row of matrix , and the vector also increases by 1 row, with an additional element at the end. The added element is .

[0040] S8, taking the numerical design variables and the categorical design variables corresponding to the minimum total sound pressure level response in the training sample set as the optimal design scheme of the power plant cooling system.

[0041] The application provides a mixed variable optimization design method for a power device cooling system. The method maps ordered category type variables to one-dimensional hidden space and unordered category type variables to high-dimensional hidden space, retains the essential characteristics of different types of variables, avoids the feature loss or unreasonable association caused by variable parameterization in traditional methods, accurately describes the coupling mechanism of the two types of variables, accurately reflects the comprehensive influence of different variable combinations on the acoustic performance of the cooling system, significantly improves the fitting precision and generalization ability of the model, and provides a reliable model basis for subsequent optimization. The training sample set is trained by using a hidden space Gaussian process model, high-efficiency iterative optimization is performed on the mixed variables, the sample set is iteratively updated, and the termination condition is dynamically judged, so that the redundant calculation amount is effectively reduced, and the problem of rapid increase in calculation amount and long optimization period in the traditional method is avoided. Meanwhile, the Gaussian process model has strong nonlinear fitting and prediction ability, can quickly focus on the optimal variable combination area in the iteration process, improves the search efficiency of the global optimal solution, and ensures that the ideal optimization result is efficiently obtained within the preset threshold. The application takes the total sound pressure level response as the core optimization target, realizes the accurate mapping of mixed variables and acoustic performance through the whole process of parameterized model acoustic analysis, hidden space model training and iterative optimization, and designs a scientific parameterized mapping scheme for ordered and unordered category type variables, so that the method can adapt to different types and different quantities of mixed variable combination scenes, and is suitable for the cooling system design of various engines, motors and other power devices.

[0042] In some embodiments of the application, step S3 specifically comprises: for an ordered category type design variable with L category values, sorting the label values of the ordered category type design variable from small to large to obtain a one-dimensional variable sequence ; introducing an ordered coordinate point sequence containing L one-dimensional hidden space coordinate points (ordered coordinate points in one-dimensional hidden space) to one-to-one map the parameterized values of the ordered category type design variables in the one-dimensional variable sequence ; the value of the one-dimensional hidden space coordinate point is in the interval ; and , , the values of the remaining one-dimensional hidden space coordinate points satisfy . It can be understood that each ordered category type design variable needs to perform step S3 to form the one-dimensional variable sequence and the ordered coordinate point sequence , and the values of L of different ordered category type design variables can be different or the same.

[0043] By sorting the ordered categorical design variables, a one-dimensional hidden space coordinate point sequence is constructed for one-to-one mapping, ensuring that the hierarchical relationship of the ordered variables is not lost in the parameterization process. The value of the one-dimensional hidden space coordinate point is limited in the interval [0, 1], and the first and last coordinates are fixed as 0 and 1, and the intermediate coordinates are strictly increasing, which not only realizes the standardized expression of the ordered variables, but also accurately preserves the ordered association characteristics between variables. Avoid the problem of distortion of ordered information in the traditional parameterization method, so that the subsequent model training can accurately capture the gradient influence of the ordered variables on the acoustic performance of the cooling system, providing a reliable ordered variable input basis for the optimization model.

[0044] In some embodiments of the present application, step S4 specifically comprises: for an unordered categorical design variable with M category values, the sequence composed of the marker values of the M unordered categorical design variables is represented as an unordered variable sequence ; Since there is no order difference between the unordered categorical design variables, the unordered variable sequence can be randomly sorted when determining the arrangement order, and the order is fixed after sorting, and the subsequent order is unchanged. A multi-dimensional unordered coordinate point sequence containing multi-dimensional unordered coordinate points in the high-dimensional hidden space is introduced to one-to-one map the parameterized values of the unordered categorical design variables in the sequence , wherein the non-zero coordinate component values in each coordinate point are in the interval . Since there is no influence between the unordered categorical design variables, the non-zero coordinate component values of each multi-dimensional hidden space coordinate point in the multi-dimensional unordered coordinate point sequence are not in the same dimension, and there is no basis for comparison and influence between them. It can be understood that each unordered categorical design variable needs to perform step S4 to form an unordered variable sequence and a multi-dimensional unordered coordinate point sequence , and the values of of different unordered categorical design variables can be different or the same.

[0045] For unordered categorical design variables, M M-dimensional hidden space coordinate point sequences are used for mapping, and through the differential design of non-zero coordinates of different dimensions, the effective differentiation of different category variables is realized, and unreasonable numerical association is avoided. The non-zero coordinate component values are limited in the interval [0, 1], which ensures the consistency and standardization of variable parameterization. This step completely preserves the essential characteristics of unordered variables, enabling the model to accurately identify the independent influence of different category variables on the total sound pressure level response, and improving the scientificity and accuracy of unordered variable processing in mixed variable optimization.

[0046] In some embodiments of the present application, in step S5, the hyperparameters of the latent space Gaussian process model to be determined include: a regression constant term , a process variance , a characteristic scale coefficient hidden in a correlation function, a value of a one-dimensional latent space coordinate point corresponding to a category of an ordered categorical design variable , and a non-zero coordinate component value of a high-dimensional latent space coordinate point corresponding to a category value of an unordered categorical design variable .

[0047] The types of hyperparameters required by the latent space Gaussian process model are determined, including the regression constant term, the process variance, the characteristic scale coefficient, and the latent space coordinates corresponding to each category variable, forming a complete hyperparameter system. The model training objective is clearer, and the mixed characteristics of numerical and categorical variables and their comprehensive action mechanism on the acoustic response can be fully captured.

[0048] In some embodiments of the present application, the hyperparameters can be obtained as follows:

[0049] By maximizing the log-likelihood function, the covariance matrix corresponding to the maximum of the log-likelihood function is obtained ; the log-likelihood function is:

[0050] ;

[0051] The covariance matrix of , where is the number of samples, the process variance , the characteristic scale coefficient, the value of the one-dimensional latent space coordinate point , and the non-zero coordinate component value of the high-dimensional latent space coordinate point are all hidden in the covariance matrix . is the log-likelihood function. is the total sound pressure level response vector.

[0052] The optimization algorithm can be used to maximize the log-likelihood function as the optimization objective, thereby obtaining the optimized and screened hyperparameters. The optimization algorithm can be a particle swarm optimization algorithm or a genetic algorithm.

[0053] The regression constant term is calculated by the following formula:

[0054] ;

[0055] is a vector with all elements being 1, and T represents the transpose of the vector. is the total sound pressure level response vector.

[0056] By maximizing the log-likelihood function to obtain hyperparameter values, the correlation information between the total sound pressure level response and the covariance matrix in the training sample set is fully utilized. Taking into account the number of samples, the dimension of the response vector, and the characteristics of the covariance matrix, the hyperparameters can be adaptively adjusted to fit the data distribution pattern, providing a core guarantee for the model's prediction accuracy.

[0057] The The Line 1 The elements of the column are:

[0058] ;

[0059] For the first Response of a sample With the Response of a sample The correlation function between them includes the feature scale coefficient and the values ​​of the coordinates of the one-dimensional latent space points. Non-zero coordinate component values ​​of coordinate points in high-dimensional hidden space .

[0060] The definition of the elements of the covariance matrix clearly defines the correlation between sample responses and implicitly includes key parameters such as process variance, feature scaling coefficients, and latent space coordinates, achieving organic integration of multiple parameters. This enables the model to fully explore the potential correlations in the sample data, improves the model's ability to characterize the mapping relationship between mixed variables and acoustic responses, and provides a reliable model foundation for subsequent iterative optimization.

[0061] In some embodiments of the present invention, the formula for the relevant function is as follows:

[0062] ;

[0063] For the first Distance components of each design variable,

[0064] For numerical design variables , ;

[0065] For ordered categorical design variables , ;

[0066] For unordered categorical design variables , ;

[0067] For the first Characteristic scaling coefficients of each design variable; The total number of categories for an ordered categorical design variable. The total number of types of unordered categorical design variables. For the i-th sample Numerical design variable values ​​for each design variable; For the first The first sample Numerical design variable values ​​for each design variable; For the i-th sample, the th The ordinal number of the ordered coordinate point sequence corresponding to each design variable. For the first in an ordered sequence of coordinate points The values ​​of each coordinate point; For the first The first sample The ordinal number of the ordered coordinate point sequence corresponding to each design variable. For the first in an ordered sequence of coordinate points The values ​​of each coordinate point; For the i-th sample The ordinal number of the multidimensional unordered coordinate point sequence corresponding to each design variable. For the multidimensional unordered coordinate point sequence, the first... Non-zero coordinate component values ​​of each coordinate point; For the first The first sample The ordinal number of the multidimensional unordered coordinate point sequence corresponding to each design variable. For the multidimensional unordered coordinate point sequence, the first... Non-zero coordinate component values ​​of each coordinate point; Indicates the first A unit vector with 1 element and 0 elements; Indicates the first A unit vector with one element being 1 and the rest being 0.

[0068] for and ,when When, it corresponds to numerical design variables; This corresponds to ordered categorical design variables; This corresponds to unordered categorical design variables. Typically, the input matrix... The parameters for each sample are also arranged in this order, i.e., the input matrix. The elements in each row are also arranged as described above, which facilitates parameter retrieval. For example... That is, a matrix can be represented The i-th row of the middle Numerical design variable values ​​for each design variable. For example... For matrix The i-th row of the middle The ordinal number of the ordered coordinate point sequence corresponding to each design variable.

[0069] The correlation function integrates the distance components of numerical, ordered categorical, and unordered categorical design variables through a product, achieving precise quantification of the influence weights of different types of variables. Differentiated distance component calculation logics are defined for each of the three types of variables: numerical variables are based on absolute value differences, ordered categorical variables on latent space coordinate differences, and unordered categorical variables on the L2 norm of high-dimensional latent space vectors, ensuring the specificity and rationality of the correlation characterization for each type of variable. The function introduces a feature scaling coefficient, which can adaptively adjust the degree of influence of different design variables on the total sound pressure level response, improving the model's adaptability to variable coupling relationships.

[0070] In some embodiments of the present invention, in step S7, the input variables when the improved desired acquisition function is maximized are obtained by maximizing the improved desired acquisition function. ;

[0071] The improved desired acquisition function is as follows:

[0072] ;

[0073] The optimized input variables can be obtained by optimizing the algorithm with the goal of maximizing the improvement of the desired acquisition function. The optimization algorithm can be a mixed-variable particle swarm optimization algorithm or a mixed-variable genetic algorithm, etc.

[0074] Input variables The posterior prediction mean of the corresponding latent space Gaussian process model; For training sample set The minimum value of the response is the minimum value among all elements in the total sound pressure level response vector y. The cumulative distribution function of the standard normal distribution. is the probability density function of the standard normal distribution; Input variables The posterior prediction standard deviation of the corresponding latent space Gaussian process model.

[0075] Specifically, and It can be calculated using the following formula:

[0076]

[0077] for The related function vector, its first... Each element is a related function. ; .Will Input variables in replace It can be calculated.

[0078] An improved expected acquisition function is combined with the posterior predicted mean and standard deviation of a latent space Gaussian process model. An iterative criterion is constructed using the cumulative distribution function and probability density function of a standard normal distribution. This function targets the minimum total sound pressure level response in the training sample set, guiding variable iteration towards regions with superior acoustic performance. Simultaneously, the standard deviation term considers the potential optimization value of unexplored regions, effectively preventing iteration from getting trapped in local optima. The iterative mechanism eliminates the need for additional discretization of categorical variables, allowing direct co-optimization with numerical variables, adapting to the characteristics of mixed variables, and significantly improving iteration efficiency. By maximizing this acquisition function to obtain the optimized input variables, each iteration ensures targeted supplementation of high-quality samples, accelerating the convergence speed of the training sample set and enabling the optimization process to efficiently approach the global optimum within a preset threshold.

[0079] This invention also provides a hybrid variable optimization design system for a power unit cooling system, used to implement a hybrid variable optimization design method for a power unit cooling system, comprising: a matrix generation module for generating a matrix containing... Input matrix of initial training samples , The size is Training sample generation module, used to combine The input matrix formed by the initial samples Corresponding total sound pressure level response To form a training sample set The ordered variable mapping module maps the labeled values ​​of ordered categorical design variables to one-dimensional ordered coordinate points in a one-dimensional latent space; the unordered variable mapping module maps the labeled values ​​of unordered categorical design variables to multi-dimensional unordered coordinate points in a high-dimensional latent space; the training module is used to map the values ​​of unordered categorical design variables to multi-dimensional unordered coordinate points in a high-dimensional latent space based on the training sample set. Training a latent space Gaussian process model; an iteration module for iterating over numerical and categorical design variables to obtain the iterated input variables. And obtain the input variables after iteration. Corresponding total sound pressure level response The loop module is used to update the number of samples. ,Will Merged into the training sample set ,judge Whether it is greater than the preset threshold N; Optimize the design scheme output module, used to process the training sample set The numerical design variables and the category design variables corresponding to the minimum total sound pressure level response are taken as the optimized design scheme of the power device cooling system.

[0080] The application further provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the power device cooling system mixed variable optimization design method.

[0081] The above only describes the preferred embodiments of the present application and is not used to limit the present application, and various modifications and changes can be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A hybrid variable optimization design method for a power unit cooling system, characterized in that, Includes the following steps: S1, generates a sequence containing Input matrix of initial training samples , The size is , The total number of types of numerical design variables. The total number of categories for categorical design variables; S2, combined The input matrix formed by the initial samples Corresponding total sound pressure level response To form a training sample set ; S3 maps the labeled values ​​of ordered categorical design variables to ordered coordinate points in a one-dimensional latent space; S4 maps the labeled values ​​of unordered categorical design variables to unordered coordinate points in a high-dimensional latent space; S5, based on the training sample set Training a latent space Gaussian process model; S6 iterates through the numerical and categorical design variables to obtain the iterated input variables. And obtain the input variables after iteration. Corresponding total sound pressure level response ; S7, Update sample count ,Will Merged into the training sample set ,judge Is it greater than the preset threshold N? If yes, proceed to step S8; otherwise, return to step S3. S8, training sample set The numerical and categorical design variables corresponding to the minimum total sound pressure level response are used as the optimal design scheme for the power unit cooling system. Step S3 specifically includes: For an ordered categorical design variable with L class values, sort the class values ​​of the ordered categorical design variable from smallest to largest to obtain a one-dimensional variable sequence. ; Introducing include An ordered sequence of coordinate points in a one-dimensional latent space To map one-to-one one-dimensional variable sequences The parameterized values ​​of ordered categorical design variables in the interval; the values ​​of one-dimensional latent space coordinate points in the interval. Inside; and , The values ​​of the remaining one-dimensional latent space coordinates satisfy ; Step S4 specifically includes: For an unordered categorical design variable with M class values, the sequence of label values ​​of the M unordered categorical design variables is represented as the unordered variable sequence. ; Introducing include indivual A multidimensional unordered sequence of coordinate points in hidden space One-to-one mapping sequence The parameterized values ​​of unordered categorical design variables in the model, where the non-zero coordinate component values ​​at each coordinate point are... All within the range Inside; In step S5, the hyperparameters of the latent space Gaussian process model that need to be determined through training include: the regression constant term. Process variance The feature scale coefficients implicit in the correlation function, and the values ​​of the one-dimensional latent space coordinates corresponding to the categories of ordered categorical design variables. The non-zero coordinate component values ​​of the high-dimensional latent space coordinate points corresponding to the category values ​​of unordered categorical design variables. .

2. The hybrid variable optimization design method for a power unit cooling system according to claim 1, characterized in that, The hyperparameters can be obtained in the following way: By maximizing the log-likelihood function, we obtain the covariance matrix corresponding to the maximization of the log-likelihood function. ; The log-likelihood function is: ； for The covariance matrix, The process variance is the number of samples. Feature scaling coefficients and the values ​​of coordinates in the one-dimensional latent space. Non-zero coordinate component values ​​of coordinate points in high-dimensional hidden space All are implicit in the covariance matrix middle; The regression constant term It is calculated using the following formula: ； For all elements to be 1 vector.

3. The hybrid variable optimization design method for a power unit cooling system according to claim 2, characterized in that, The covariance matrix The Line 1 The elements of the column are: ； For the first Response of a sample With the Response of a sample The correlation function between them includes the feature scale coefficient and the values ​​of the coordinates of the one-dimensional latent space points. Non-zero coordinate component values ​​of coordinate points in high-dimensional hidden space .

4. The hybrid variable optimization design method for a power unit cooling system according to claim 3, characterized in that, The formula for the relevant function is as follows: ； For the first Distance components of each design variable, For numerical design variables , ; For ordered categorical design variables , ; For unordered categorical design variables , ; For the first Characteristic scaling coefficients of each design variable; The total number of categories for an ordered categorical design variable; For the i-th sample Numerical design variable values ​​for each design variable; For the first The first sample Numerical design variable values ​​for each design variable; For the i-th sample The ordinal number in the ordered coordinate point sequence corresponding to each design variable; For the first The first sample The ordinal number in the ordered coordinate point sequence corresponding to each design variable; For the i-th sample The ordinal number of the multidimensional unordered coordinate point sequence corresponding to each design variable; For the first The first sample The ordinal number of the multidimensional unordered coordinate point sequence corresponding to each design variable; Indicates the first A unit vector with 1 element and 0 elements; Indicates the first A unit vector with one element being 1 and the rest being 0.

5. The hybrid variable optimization design method for a power unit cooling system according to claim 1, characterized in that, In step S7, the input variables when the improved desired acquisition function is maximized are obtained by maximizing the improved desired acquisition function. ; The improved desired acquisition function is as follows: ； Input variables The posterior prediction mean of the corresponding latent space Gaussian process model; For training sample set The minimum value of the response. The cumulative distribution function of the standard normal distribution. The probability density function is the standard normal distribution. Input variables The posterior prediction standard deviation of the corresponding latent space Gaussian process model.

6. A hybrid variable optimization design system for a power unit cooling system, used to implement the hybrid variable optimization design method for a power unit cooling system according to any one of claims 1 to 5, characterized in that, include: The matrix generation module is used to generate matrices containing... Input matrix of initial training samples , The size is ; Training sample generation module, used to combine The input matrix formed by the initial samples Corresponding total sound pressure level response To form a training sample set ; The ordered variable mapping module is used to map the labeled values ​​of ordered categorical design variables to one-dimensional ordered coordinate points in a one-dimensional latent space; The unordered variable mapping module is used to map the labeled values ​​of unordered categorical design variables to multidimensional unordered coordinate points in a high-dimensional latent space; The training module is used to train the training sample set. Training a latent space Gaussian process model; The iteration module is used to iterate over numerical and categorical design variables to obtain the iterated input variables. And obtain the input variables after iteration. Corresponding total sound pressure level response ; The loop module is used to update the number of samples. ,Will Merged into the training sample set ,judge Is it greater than the preset threshold N? The optimized design output module is used to process the training sample set. The numerical and categorical design variables corresponding to the minimum total sound pressure level response are used as the optimization design scheme for the power unit cooling system.

7. A storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the hybrid variable optimization design method for the power unit cooling system as described in any one of claims 1 to 5.

Images