A method and system for optimizing a compressor interstage plenum seal structure

Abstract

The present application relates to the technical field of simulation aided design, in particular to a kind of optimization method and system of compressor interstage plenum sealing structure, comprising: determining the modeling parameter of plenum sealing structure;Obtain relevant modeling parameters;Build neural network, and train;Obtain the relevant modeling parameter corresponding to the maximum compressor efficiency and the minimum plenum wind resistance temperature rise;Build optimized compressor interstage plenum sealing structure.The present application comprehensively considers the influence of the change of each local position in plenum sealing structure on leakage flow, to improve the negative influence of leakage flow on compressor performance to the greatest extent.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of simulation aided design, in particular to a method and system for optimizing a sealing structure of a compressor inter-stage cavity. BACKGROUND

[0002] There is always a certain gap between two components with relative motion inside an aero-engine, and the abnormal flow of gas or liquid in the gap will affect the efficiency and normal working time of the engine to some extent. The shroud type stator, which has good mechanical strength, is a commonly used structure in the compressor at present. However, it will face severe end region problems at high load: the complex reverse cavity leakage flow will be formed between the inner shroud of the stator and the rotor hub groove due to the large pressure difference before and after the stator. Although the labyrinth seal is designed to limit excessive leakage, the cavity leakage flow after doing work on the rotating wall will still flow back to the mainstream channel from the front of the stator, affecting the secondary flow at the root of the stator, and then affecting the performance of the compressor. Therefore, it is very important to reduce the negative impact of leakage flow on the performance of the compressor.

[0003] The change of the sealing structure of the inter-stage cavity will have a greater impact on the gas flow state in the cavity and the compressor cascade channel, and the change of different positions in the cavity will also have different effects on the leakage flow and the main flow. At present, the optimization design of the sealing structure of the cavity is mostly carried out locally, and the mutual influence between the local structures cannot be matched well, resulting in high wind resistance temperature rise of the cavity and affecting the performance of the compressor.

[0004] Therefore, it is necessary to provide a method and system for optimizing the sealing structure of the inter-stage cavity of the compressor to solve the above problems. SUMMARY

[0005] In order to solve the problem that the optimization design of the sealing structure of the cavity is mostly carried out locally at present, the mutual influence between the local structures cannot be matched well, resulting in high wind resistance temperature rise of the cavity and affecting the performance of the compressor, the present application provides a method and system for optimizing the sealing structure of the inter-stage cavity of the compressor to solve the existing problems.

[0006] The first aspect of the present application provides a method for optimizing the sealing structure of the inter-stage cavity of the compressor, which adopts the following technical scheme, comprising:

[0007] determining the modeling parameters of the sealing structure of the cavity;

[0008] obtaining a plurality of cavity sealing structure models according to the preset modeling parameter range; obtaining the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure model; and performing correlation analysis on the modeling parameters and the compressor efficiency, and the modeling parameters and the cavity wind resistance temperature rise to obtain the relevant modeling parameters in the modeling parameters;

[0009] Based on the related modeling parameters under the modeling of each cavity sealing structure, and the corresponding compressor efficiency and cavity wind resistance temperature rise, a database is constructed; a neural network is constructed, and the trained target neural network is obtained based on the database training of the neural network;

[0010] The target neural network is used as a proxy model, the compressor efficiency and the cavity wind resistance temperature rise are used as optimization objectives, a multi-objective optimization algorithm is used to iteratively optimize the related modeling parameters of the database, and the database is updated according to the modeling parameters generated after each iterative optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise, until the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are obtained;

[0011] The related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are used as optimal modeling parameters, and an optimized compressor inter-stage cavity sealing structure is constructed based on the optimal modeling parameters.

[0012] In a further technical solution of the present application, the modeling parameters of the cavity sealing structure include: the distance between the side wall of the upstream rectangular cavity away from the static blade and the side wall of the upstream leakage flow passage away from the static blade, the distance between the side wall of the upstream rectangular cavity close to the static blade and the side wall of the upstream leakage flow passage close to the static blade, the distance between the side wall of the downstream rectangular cavity away from the static blade and the side wall of the downstream leakage flow passage away from the static blade, the distance between the side wall of the downstream rectangular cavity close to the static blade and the side wall of the downstream leakage flow passage close to the static blade, the distance between the adjacent two bars, the distance between the side wall of the upstream rectangular cavity close to the static blade and the bar close to the upstream rectangular cavity, the distance between the side wall of the downstream rectangular cavity close to the static blade and the bar close to the downstream rectangular cavity, the distance between the bar top and the bottom of the static blade, the bar top width, the bar bevel length, the distance from the bar tip of each bar to the rotation center, the distance from the upper wall surface of the upstream rectangular cavity to the rotation center and the distance from the upper wall surface of the downstream rectangular cavity to the rotation center.

[0013] In a further technical solution of the present application, according to the preset modeling parameter range, the steps of obtaining a plurality of cavity sealing structure modeling are: Latin hypercube sampling is performed on the modeling parameters within the preset modeling parameter range, and a plurality of cavity sealing structure modeling is generated.

[0014] In a further technical solution of the present application, the steps of obtaining the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure modeling are:

[0015] A simulation model corresponding to the cavity sealing structure modeling is constructed;

[0016] Numerical simulation calculation is performed on the simulation model, and the compressor efficiency and the cavity wind resistance temperature rise corresponding to each cavity sealing structure modeling are obtained.

[0017] The further technical solution of the application is related to the modeling parameters, which are the distance between the side wall of the upstream rectangular cavity away from the static blade and the side wall of the upstream leakage passage away from the static blade, the distance between the side wall of the upstream rectangular cavity close to the static blade and the side wall of the upstream leakage passage close to the static blade, the distance between the side wall of the downstream rectangular cavity away from the static blade and the side wall of the downstream leakage passage away from the static blade, the distance between the adjacent two grid teeth, the distance between the side wall of the downstream rectangular cavity close to the static blade and the grid tooth close to the downstream rectangular cavity, the distance between the top of the grid tooth and the bottom of the static blade, the width of the top of the grid tooth, the length of the hypotenuse of the grid tooth, the distance between the upper wall surface of the upstream rectangular cavity and the rotation center, and the distance between the upper wall surface of the downstream rectangular cavity and the rotation center.

[0018] The further technical solution of the application is related to the modeling parameters and the compressor efficiency, the modeling parameters and the cavity wind resistance temperature rise, and the steps for obtaining the related modeling parameters in the modeling parameters are as follows:

[0019] The significant level values corresponding to the modeling parameters and the compressor efficiency and the modeling parameters and the cavity wind resistance temperature rise are obtained respectively by using the Spearman correlation analysis algorithm.

[0020] The modeling parameters with the significant level values less than the preset significant level value threshold are taken as the related modeling parameters.

[0021] The further technical solution of the application is that the neural network adopts a radial basis neural network.

[0022] The further technical solution of the application is that the multi-objective optimization algorithm adopts an NSGA-II genetic algorithm.

[0023] The second aspect of the application provides an optimization system of a compressor inter-stage cavity sealing structure, which comprises:

[0024] A modeling parameter module is configured to determine the modeling parameters of the cavity sealing structure.

[0025] A related modeling parameter acquisition module is configured to obtain a plurality of cavity sealing structure models according to a preset modeling parameter range, obtain the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure model, and perform correlation analysis on the modeling parameters and the compressor efficiency and the modeling parameters and the cavity wind resistance temperature rise to obtain the related modeling parameters in the modeling parameters.

[0026] A neural network module is configured to construct a database based on the related modeling parameters and the corresponding compressor efficiency and cavity wind resistance temperature rise under each cavity sealing structure model, construct a neural network, and train the neural network based on the database to obtain a trained target neural network.

[0027] The target optimization module is configured to use the target neural network as a surrogate model, take the compressor efficiency and the cavity wind resistance temperature rise as optimization targets, use a multi-objective optimization algorithm to iteratively optimize the related modeling parameters in the database, and update the database according to the related modeling parameters generated after each iteration optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise until the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are obtained.

[0028] The modeling module is configured to take the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise as optimal modeling parameters, and construct an optimized compressor inter-stage cavity sealing structure based on the optimal modeling parameters.

[0029] The present application has the following advantages:

[0030] The present application takes the compressor inter-stage cavity sealing structure as a whole for optimization, performs global optimization on the basis of parameterization of the inter-stage cavity sealing structure, and obtains an inter-stage cavity sealing structure capable of improving the leakage flow characteristics and the compressor performance. The method has the advantages of comprehensively considering the influence of changes in each local position in the cavity sealing on the leakage flow, and improving the negative influence of the leakage flow on the compressor performance to the maximum extent. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0032] Figure 1 The flowchart of the optimization method of the compressor inter-stage cavity sealing structure of the present application;

[0033] Figure 2 The detailed flowchart of the optimization method of the compressor inter-stage cavity sealing structure in the embodiment of the present application;

[0034] Figure 3 The parameterization schematic diagram of the inter-stage cavity sealing structure in the embodiment of the present application;

[0035] Figure 4 The correlation analysis result in the embodiment of the present application;

[0036] Figure 5 The optimization result schematic diagram of the compressor inter-stage cavity sealing structure in the embodiment of the present application;

[0037] Figure 6The relative change of the cavity leakage characteristics of the cavity sealing structure after optimization by the optimization method in the embodiment of the present application relative to the cavity sealing structure before optimization. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0039] At present, the optimization design research on the cavity sealing structure mainly focuses on the improvement of local areas, for example, the adjustment of the cavity inlet, outlet or specific wall shape. These local optimization measures improve the characteristics of the cavity leakage flow to some extent, but due to the changes in the structures of different parts of the cavity, the local optimization often fails to comprehensively consider the negative impact of the leakage flow on the end region flow. The structural changes at different positions of the cavity have significantly different influences on the flow rate, flow direction of the leakage flow and the interaction mode with the main flow. For example, the adjustment of the cavity inlet shape may change the initial momentum of the leakage flow, and the changes in the internal geometry of the cavity may affect the flow path and turbulence characteristics of the leakage flow. Therefore, only local optimization of several parts of the cavity can hardly achieve the best matching of the leakage flow and the main flow. In order to minimize the negative impact of the cavity leakage flow on the main flow and fully exert the potential positive role of the cavity leakage flow on the end region flow, it is necessary to globally optimize the shape of the cavity structure. The global optimization design not only needs to consider the geometric parameters of each part of the cavity, but also needs to comprehensively consider the interaction mechanism of the leakage flow and the main flow. Through a multi-objective optimization method, the optimal cavity shape is found, and therefore the embodiment of the optimization method of the cavity sealing structure of the compressor inter-stage cavity is provided, as shown in Figure 1 and Figure 2 , which comprises:

[0040] S1, determining the shape parameters of the cavity sealing structure;

[0041] For example, in a specific embodiment, since the three-dimensional cavity sealing structure is obtained by rotation, in order to make parameterization more convenient, the process of the embodiment is performed on a two-dimensional structure. First, the two-dimensional cavity sealing structure is discretized into a plurality of feature points, and the two-dimensional cavity sealing structure is constructed by connecting the feature points, and then the three-dimensional cavity sealing structure is obtained by rotation. The specific parameterization result is shown in Figure 3 , and the blue frame line is the cavity sealing structure, and the parameterization is to construct the two-dimensional blue frame line. Figure 3The significance of each shape parameter is the distance between the associated feature points. By changing the size of the shape parameter, the distance between the feature points can be controlled, and thus the entire cavity sealing structure can be changed. Therefore, in this embodiment, the shape parameters of the cavity sealing structure include: the distance between the side wall of the upstream rectangular cavity away from the stator vane and the side wall of the upstream leakage flow passage away from the stator vane G 1. the distance between the side wall of the upstream rectangular cavity close to the stator vane and the side wall of the upstream leakage flow passage close to the stator vane G 2. the distance between the side wall of the downstream rectangular cavity away from the stator vane and the side wall of the downstream leakage flow passage away from the stator vane G 3. the distance between the side wall of the downstream rectangular cavity close to the stator vane and the side wall of the downstream leakage flow passage close to the stator vane G 4. the distance between two adjacent teeth B 1. the distance between the side wall of the upstream rectangular cavity close to the stator vane and the tooth close to the upstream rectangular cavity B 2. the distance between the side wall of the downstream rectangular cavity close to the stator vane and the tooth close to the downstream rectangular cavity B 3. the distance between the tooth top of the tooth and the bottom of the stator vane c 4. the tooth top width of the tooth e 5. the hypotenuse length of the tooth H 6. the distance between the upper wall of the downstream rectangular cavity (the wall away from the rotation center) and the rotation center R 7. the distance between the upper wall of the upstream rectangular cavity (the wall away from the rotation center) and the rotation center R 8. by changing the size of the shape parameter of the cavity sealing structure, the cavity sealing structure can be controlled.

[0042] It should be noted that, as shown in Figure 3 the embodiment, by changing the size of the distance between the side wall of the upstream rectangular cavity away from the stator vane and the side wall of the upstream leakage flow passage away from the stator vane G 1. the distance between the side wall of the upstream rectangular cavity close to the stator vane and the side wall of the upstream leakage flow passage close to the stator vane G 2. the distance between the side wall of the downstream rectangular cavity away from the stator vane and the side wall of the downstream leakage flow passage away from the stator vane G 3. and the distance between the side wall of the downstream rectangular cavity close to the stator vane and the side wall of the downstream leakage flow passage close to the stator vane G 4, the size of the cavity width of the cavity sealing structure can be changed; by changing the distance between two adjacent teeth B 1. the distance between the side wall of the upstream rectangular cavity close to the stator vane and the tooth close to the upstream rectangular cavity B 2. and the distance between the side wall of the downstream rectangular cavity close to the stator vane and the tooth close to the downstream rectangular cavity B 3, the position of the three teeth of the cavity sealing structure can be controlled; by changing the distance between the tooth top of the tooth and the bottom of the stator vane cThe gap between the tooth tips of the grate can be controlled; the tooth tip width e can be controlled; the height of the grate can be controlled by changing the length H of the inclined side; and the maximum distance between the downstream rectangular cavity and the rotation axis can be changed. R 5. The maximum distance between the upstream rectangular cavity and the rotation axis R 6 can change the cavity height of the cavity sealing structure.

[0043] For example, in one specific embodiment, the coordinates of the unknown feature point are obtained through a self-compiled function relational program, specifically expressed as:

[0044]

[0045] In the formula, i Indicates the first i One known feature point: j Indicates the first j One unknown feature point; using the coordinates and shape parameters of the known feature points, through a function F xj and F yj To obtain the x and y coordinates of the unknown point, i.e. x j and y j The cavity shape can be constructed based on the coordinates of all feature points and the shape parameters.

[0046] S2. Obtain relevant styling parameters;

[0047] Specifically, based on the preset range of design parameters, several cavity sealing structure designs are obtained; the compressor efficiency and cavity resistance temperature rise under each cavity sealing structure design are obtained; correlation analysis is performed on the design parameters and compressor efficiency, and the design parameters and cavity resistance temperature rise to obtain relevant design parameters in the design parameters.

[0048] For example, in one specific embodiment, the step of obtaining several cavity sealing structure shapes according to the preset shape parameter range is as follows: Latin hypercube sampling is performed on the shape parameters within the preset shape parameter range to generate several cavity sealing structure shape samples. The variation range of the 12 shape parameters is defined under the premise of maintaining the basic structure of the cavity sealing. The specific preset shape parameter range is shown in Table 1, and there are 100 cavity sealing structure shape samples.

[0049] Table 1

[0050]

[0051] For example, in one specific embodiment, the steps for obtaining the compressor efficiency and cavity resistance temperature rise under each cavity sealing structure design are as follows: constructing a simulation model corresponding to the cavity sealing structure design; performing numerical simulation calculations on the simulation model to obtain the compressor efficiency and cavity resistance temperature rise corresponding to each cavity sealing structure design. It should be noted that, since cavity resistance temperature rise, as one of the performance parameters, can take into account the safety issues caused by excessive temperature rise inside the compressor, and compressor efficiency directly reflects the compressor performance, this embodiment uses compressor efficiency and cavity resistance temperature rise as compressor performance parameters.

[0052] For example, in one specific embodiment, the step of performing correlation analysis on the design parameters and compressor efficiency, and on the design parameters and cavity resistance temperature rise, to obtain the relevant design parameters is as follows: using the Spearman correlation analysis algorithm, the corresponding significance level values ​​between the design parameters and compressor efficiency, and between the design parameters and cavity resistance temperature rise are obtained respectively. P ; the significance level value P The styling parameters that meet the correlation criteria are considered as relevant styling parameters (i.e., at the significance level). P When the significance level is less than a preset significance level threshold, the significance level value satisfies the correlation condition. Specifically, in this embodiment, the significance level threshold is 0.05, that is, when the significance level value is less than a preset significance level threshold, the significance level value satisfies the correlation condition. P When the value is less than 0.05, it indicates that the two are significantly correlated. The results of the correlation analysis are shown in Table 2.

[0053] Table 2

[0054]

[0055] As shown in Table 2, correlation analysis reveals that among the styling parameters... c , B 1 、B 3. G 1. G 3 is significantly correlated with compressor efficiency; among the design parameters G 1. G 2. G 3. B 3. c, e , H , R 5. R 6. This is significantly related to the compressor cavity resistance and temperature rise. Therefore, in this embodiment, the relevant design parameters are: the distance between the sidewall of the upstream rectangular cavity away from the stationary vane and the sidewall of the upstream leakage channel away from the stationary vane. G 1. The distance between the sidewall of the upstream rectangular cavity near the stator vane and the sidewall of the upstream leakage channel near the stator vane. G 2. The distance between the sidewall of the downstream rectangular cavity away from the stator vane and the sidewall of the downstream leakage channel away from the stator vane. G3, distance between two adjacent bars B 1, distance between the side wall of the downstream rectangular cavity close to the vane and the bars close to the downstream rectangular cavity B 3, distance between the top of the bars and the bottom of the vane c , tooth top width of the bars e , length of the inclined edge of the bars H , distance between the upper wall of the downstream rectangular cavity and the rotation center R 5, distance between the upper wall of the upstream rectangular cavity and the rotation center R 6. The correlation coefficient between the relevant modeling parameters and the compressor performance parameters is shown in the table as follows: Figure 4 When the correlation coefficient is positive, it indicates that the two are positively correlated, and the compressor performance parameter will increase with the increase of the relevant modeling parameter. When the correlation coefficient is negative, it indicates that the two are negatively correlated, and the compressor performance parameter will decrease with the increase of the relevant modeling parameter. Among them, c , B 3, G 1, G 3 is negatively correlated with the compressor efficiency, that is, c , B 3, G 1, G 3 decreases, the compressor efficiency increases, c , B 3, G 1, G 3 increases, the compressor efficiency decreases; B 1 is positively correlated with the compressor efficiency, that is, B 1 increases, the compressor efficiency also increases. Among the relevant modeling parameters, G 1, G 2, G 3, H , R 5 is positively correlated with the cavity wind resistance temperature rise, that is, G 1, G 2, G 3, H , R 5 increases, the cavity wind resistance temperature rise also increases; B 3, c, e , R 6 is negatively correlated with the cavity wind resistance temperature rise, that is, B 3, c, e , R 6 increases, the cavity wind resistance temperature rise decreases.

[0056] S3, construct a neural network and train it;

[0057] Specifically, a database is constructed based on the relevant design parameters of each cavity sealing structure, as well as the corresponding compressor efficiency and cavity drag temperature rise; a neural network is constructed, and the target neural network is trained based on the database.

[0058] For example, in one specific embodiment, the neural network adopts a radial basis function (RBF) neural network. That is, in this embodiment, the Gaussian radial basis function (RBF) is used as the activation function of the hidden layer of the RBF neural network, and its mathematical expression is:

[0059] (1)

[0060] In the formula, For the first j Output values ​​of radial basis neurons; X For the relevant modeling parameters input, c j For the first radial basis function neural network j The center of each hidden layer neuron, ε j is a shape parameter used to control the width of the Gaussian radial basis function.

[0061] The output layer of the radial basis function neural network uses a linearly weighted combination, and the expression for predicting the objective function value is as follows:

[0062] (2)

[0063] In the formula, This represents the neural network's prediction of the objective function. ω j For the weights of the output layer, b For bias terms, m This represents the number of neurons in the hidden layer.

[0064] In the radial basis function neural network training process, orthogonal least squares (OLS) is used to determine the center of neurons in the hidden layer of the RBF. c j Adjusted by the nearest neighbor method ε j The gradient descent method is used to solve for the weights. ω j To minimize the prediction error, the expression is:

[0065] (3)

[0066] In the formula, σ This is the output matrix of the hidden layer. This is the true target value; This is the weight vector.

[0067] S4, obtaining the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise;

[0068] Specifically, the target neural network is taken as a surrogate model, the compressor efficiency and the cavity wind resistance temperature rise are taken as optimization objectives, the related modeling parameters of the database are iteratively optimized by using a multi-objective optimization algorithm, and the database is updated according to the modeling parameters generated after each iterative optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise, until the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are obtained.

[0069] For example, in a specific embodiment, the step of iteratively optimizing the related modeling parameters of the database by using a multi-objective optimization algorithm is as follows: in the present embodiment, the NSGA-II genetic algorithm is used as the multi-objective optimization algorithm, that is, the NSGA-II genetic algorithm is embedded in the target neural network in step S3 to perform iterative optimization, and the iterative optimization process is as follows:

[0070] S41, initialization of population:

[0071] The Latin hypercube sampling method is used to sample and generate an initial population in a set modeling parameter range P 0, to ensure that the samples are uniformly distributed in the decision space.

[0072] S42, non-dominated sorting and calculation of crowding distance:

[0073] Non-dominated sorting: the initial population is Pareto layered based on the predicted values of the target neural network, and the dominance relationship of individuals is calculated.

[0074] Crowding distance: measure the distribution density of solutions in the objective space, and avoid local aggregation. In order to maintain the diversity of the solution set, the algorithm calculates the crowding distance of the solutions in each Pareto level. Here, the solutions are the initial population divided into different Pareto levels, and the crowding distance expression is:

[0075] (4)

[0076] In the formula, is the function value of the first i+ 1 solution on the first k objective; is the crowding distance of the first i solution; K is the number of objective functions; is the function value of the first i- 1 solution on the first k objective.

[0077] S43, selection, crossover and mutation:

[0078] Tournament selection: select the best individual based on non-dominated sorting rank and crowding distance.

[0079] Simulated binary crossover (SBX): generate offspring individuals, crossover operator formula:

[0080] (5)

[0081] (6)

[0082] where, is the crossover distribution parameter, is the first offspring after crossover; is the second offspring after crossover; is the first parent participating in crossover; is the second parent participating in crossover; The calculation expression of is:

[0083] (7)

[0084] where, μ c is the crossover distribution index, used to control the similarity between offspring and parents; is a random number uniformly distributed in [0, 1].

[0085] Polynomial mutation: introduce random disturbance to enhance diversity, mutation formula:

[0086] (8)

[0087] where, is the solution after mutation; is the original solution; is the mutation amount; is the upper limit of the variable; is the lower limit of the variable.

[0088] S44, elitist strategy:

[0089] Merge the parent population and the offspring population, retain the non-dominated front solution, and ensure the convergence and diversity of the Pareto optimal solution.

[0090] S45, update the database and continue the iterative optimization until the optimization converges or the number of iterative optimization reaches the set number:

[0091] The numerical calculation of the non-dominated front solution of step S44 obtains the compressor efficiency and the cavity wind resistance temperature rise of the generated shaping parameter after each iteration optimization, that is, the related shaping parameter of the database is iteratively optimized by using the multi-objective optimization algorithm, the generated shaping parameter after each iteration optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise are obtained, and the database is dynamically updated by using the generated shaping parameter after each iteration optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise, until the iteration calculation obtains the maximum compressor efficiency and the minimum cavity wind resistance temperature rise, or the iteration optimization reaches the cycle number, and then the iteration optimization is ended.

[0092] It should be noted that in the iteration optimization in the embodiment, the initial population number of the NSGA-II genetic algorithm is 20, the evolution generation number is 100, and the maximum iteration number is 50 times. The optimal solution (i.e. the optimized shaping parameter and the corresponding compressor efficiency and cavity wind resistance temperature rise) given in each round of cycle is added to the database. The final optimization result is as shown in Figure 5 It can be seen from Figure 5 that the optimization method of the application can obtain the cavity sealing structure for improving the performance of the compressor. That is, the compressor efficiency is improved under the premise of controlling the cavity wind resistance temperature rise.

[0093] S5, constructing an optimized compressor inter-stage cavity sealing structure;

[0094] Specifically, the related shaping parameter corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise is taken as the optimal shaping parameter, and the optimized compressor inter-stage cavity sealing structure is constructed based on the optimal shaping parameter; the relative change amount of the cavity leakage characteristics of the cavity sealing structure after optimization relative to the cavity sealing structure before optimization according to the optimization method of the application is as shown in Figure 6 It can be seen from Figure 6 that the optimized shaping C can reduce the cavity leakage flow by 41.82% while keeping the cavity wind resistance temperature rise change less than 1%, and the optimized shaping D can reduce the cavity leakage flow by 58.19% while increasing the cavity wind resistance by only 11.84%. This shows that the optimized cavity sealing shaping can effectively reduce the leakage flow.

[0095] An optimization system of a compressor inter-stage cavity sealing structure comprises a modeling parameter module, a related modeling parameter acquisition module, a neural network module, a target optimization module and a modeling module, the modeling parameter module is used to determine the modeling parameters of the cavity sealing structure; the related modeling parameter acquisition module is used to obtain a plurality of cavity sealing structure models according to a preset modeling parameter range; the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure model are obtained; the correlation analysis of the modeling parameters and the compressor efficiency, the modeling parameters and the cavity wind resistance temperature rise is performed to obtain the related modeling parameters in the modeling parameters; the neural network module is used to construct a database based on the related modeling parameters under each cavity sealing structure model and the corresponding compressor efficiency and cavity wind resistance temperature rise; a neural network is constructed, and the trained target neural network is obtained by training the neural network based on the database; the target optimization module is used to take the target neural network as a proxy model, take the compressor efficiency and the cavity wind resistance temperature rise as optimization objectives, perform iterative optimization on the related modeling parameters in the database by using a multi-objective optimization algorithm, and update the database according to the modeling parameters generated after each iterative optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise until the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are obtained; the modeling module is used to take the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise as optimal modeling parameters, and construct an optimized compressor inter-stage cavity sealing structure based on the optimal modeling parameters.

[0096] The above merely describes the preferred embodiments of the present application and is not used to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of optimizing a compressor interstage plenum seal, comprising: Comprise: Determine the molding parameters of the cavity sealing structure; The molding parameters of the cavity sealing structure include: the distance between the side wall of the upstream rectangular cavity away from the static blade and the side wall of the upstream leakage passage away from the static blade, the distance between the side wall of the upstream rectangular cavity close to the static blade and the side wall of the upstream leakage passage close to the static blade, the distance between the side wall of the downstream rectangular cavity away from the static blade and the side wall of the downstream leakage passage away from the static blade, the distance between the side wall of the downstream rectangular cavity close to the static blade and the side wall of the downstream leakage passage close to the static blade, the distance between the two adjacent bars, the distance between the side wall of the upstream rectangular cavity close to the static blade and the bar close to the upstream rectangular cavity, the distance between the side wall of the downstream rectangular cavity close to the static blade and the bar close to the downstream rectangular cavity, the distance between the top of the bar and the bottom of the static blade, the width of the top of the bar, the length of the inclined edge of the bar, the distance between the upper wall of the upstream rectangular cavity and the center of rotation, and the distance between the upper wall of the downstream rectangular cavity and the center of rotation; According to the predetermined molding parameter range, obtain a plurality of cavity sealing structure molding; Obtain the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure molding; Correlation analysis is carried out on the molding parameters and the compressor efficiency, the molding parameters and the cavity wind resistance temperature rise, and the related molding parameters in the molding parameters are obtained; The related molding parameters are: the distance between the side wall of the upstream rectangular cavity away from the static blade and the side wall of the upstream leakage passage away from the static blade, the distance between the side wall of the upstream rectangular cavity close to the static blade and the side wall of the upstream leakage passage close to the static blade, the distance between the side wall of the downstream rectangular cavity away from the static blade and the side wall of the downstream leakage passage away from the static blade, the distance between the two adjacent bars, the distance between the side wall of the downstream rectangular cavity close to the static blade and the bar close to the downstream rectangular cavity, the distance between the top of the bar and the bottom of the static blade, the width of the top of the bar, the length of the inclined edge of the bar, the distance between the upper wall of the upstream rectangular cavity and the center of rotation, and the distance between the upper wall of the downstream rectangular cavity and the center of rotation; Based on the related molding parameters under each cavity sealing structure molding and the corresponding compressor efficiency and cavity wind resistance temperature rise, a database is constructed; A neural network is constructed, and the trained target neural network is obtained based on the database training of the neural network; The target neural network is used as a proxy model, the compressor efficiency and the cavity wind resistance temperature rise are used as optimization objectives, a multi-objective optimization algorithm is used to iteratively optimize the related molding parameters of the database, and the database is updated according to the molding parameters generated after each iteration optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise, until the corresponding related molding parameters when the compressor efficiency is maximum and the cavity wind resistance temperature rise is minimum; The related molding parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are used as the optimal molding parameters, and the optimized compressor inter-stage cavity sealing structure is constructed based on the optimal molding parameters.

2. The method of optimizing a containment seal for a compressor interstage pocket according to claim 1, wherein, According to the predetermined molding parameter range, a plurality of cavity sealing structure molding is obtained by: Latin hypercube sampling of the molding parameters within the predetermined molding parameter range to generate a plurality of cavity sealing structure molding.

3. The method of optimizing a containment seal for a compressor interstage pocket according to claim 1, wherein, The steps of obtaining the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure molding are: Construct a simulation model corresponding to the cavity sealing structure molding; Numerical simulation is performed on the simulation model to obtain the compressor efficiency and the cavity wind resistance temperature rise corresponding to each cavity sealing structure modeling.

4. The method of optimizing a containment seal for a compressor interstage pocket according to claim 1, wherein, The steps of obtaining the relevant modeling parameters in the modeling parameters through correlation analysis of the modeling parameters and the compressor efficiency and the modeling parameters and the cavity wind resistance temperature rise are as follows: The significant level values corresponding to the modeling parameters and the compressor efficiency and the modeling parameters and the cavity wind resistance temperature rise are obtained by using the Spearman correlation analysis algorithm. The modeling parameters with the significant level values less than the preset significant level value threshold are taken as the relevant modeling parameters.

5. The method of optimizing a containment seal for a compressor interstage pocket according to claim 1, wherein, The neural network is a radial basis neural network.

6. The method of optimizing a containment seal for a compressor interstage pocket according to claim 1, wherein The multi-objective optimization algorithm is an NSGA-II genetic algorithm.

7. A system for optimizing a compressor interstage plenum seal, comprising: The method comprises the following steps: The modeling parameter module is configured to determine the modeling parameters of the cavity sealing structure, which include the distance between the side wall of the upstream rectangular cavity away from the stator vane and the side wall of the upstream leakage passage away from the stator vane, the distance between the side wall of the upstream rectangular cavity close to the stator vane and the side wall of the upstream leakage passage close to the stator vane, the distance between the side wall of the downstream rectangular cavity away from the stator vane and the side wall of the downstream leakage passage away from the stator vane, the distance between the side wall of the downstream rectangular cavity close to the stator vane and the side wall of the downstream leakage passage close to the stator vane, the distance between the adjacent two splines, the distance between the side wall of the upstream rectangular cavity close to the stator vane and the spline close to the upstream rectangular cavity, the distance between the side wall of the downstream rectangular cavity close to the stator vane and the spline close to the downstream rectangular cavity, the distance between the spline top and the stator bottom, the spline top width, the spline hypotenuse length, the distance between the upper wall surface of the upstream rectangular cavity and the rotation center, and the distance between the upper wall surface of the downstream rectangular cavity and the rotation center. The relevant modeling parameter acquisition module is configured to acquire a plurality of cavity sealing structure models according to a preset modeling parameter range, acquire the compressor efficiency and the cavity wind resistance temperature rise under each cavity sealing structure model, and obtain the relevant modeling parameters in the modeling parameters through correlation analysis of the modeling parameters and the compressor efficiency and the modeling parameters and the cavity wind resistance temperature rise. The relevant modeling parameters include the distance between the side wall of the upstream rectangular cavity away from the stator vane and the side wall of the upstream leakage passage away from the stator vane, the distance between the side wall of the upstream rectangular cavity close to the stator vane and the side wall of the upstream leakage passage close to the stator vane, the distance between the side wall of the downstream rectangular cavity away from the stator vane and the side wall of the downstream leakage passage away from the stator vane, the distance between the adjacent two splines, the distance between the side wall of the downstream rectangular cavity close to the stator vane and the spline close to the downstream rectangular cavity, the distance between the spline top and the stator bottom, the spline top width, the spline hypotenuse length, the distance between the upper wall surface of the upstream rectangular cavity and the rotation center, and the distance between the upper wall surface of the downstream rectangular cavity and the rotation center. The neural network module is configured to construct a database based on the relevant modeling parameters and the corresponding compressor efficiency and cavity wind resistance temperature rise under each cavity sealing structure model, construct a neural network, and train the neural network based on the database to obtain a trained target neural network. The target optimization module is configured to use the target neural network as a surrogate model, take the compressor efficiency and the cavity wind resistance temperature rise as optimization targets, perform iterative optimization on the related modeling parameters in the database by using a multi-objective optimization algorithm, and update the database according to the modeling parameters generated after each iteration optimization and the corresponding compressor efficiency and cavity wind resistance temperature rise until the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise are obtained. The modeling module is configured to use the related modeling parameters corresponding to the maximum compressor efficiency and the minimum cavity wind resistance temperature rise as optimal modeling parameters, and construct an optimized compressor inter-stage cavity sealing structure based on the optimal modeling parameters.

Images