Design method and system for semi-open type fuel centrifugal pump impeller

Abstract

The invention discloses a design method and system for a semi-open type fuel centrifugal pump impeller, and relates to the technical field of semi-open type aviation fuel centrifugal pump impeller design. The design method comprises the steps that an optimization target and optimization variables influencing the optimization target are determined; using a Latin square hypercube sampling method to design sample data corresponding to multiple groups of optimization variables; establishing a semi-open fuel centrifugal pump impeller model according to the sample data corresponding to each group of optimization variables, performing numerical simulation, and establishing a database of a training agent model; training the proxy model by using a database to obtain a prediction model; optimizing an optimization target predicted by the prediction model through a multi-target genetic optimization algorithm to obtain multiple groups of optimization variables conforming to the optimization target; numerical simulation is conducted on the multiple sets of optimization variables, and a set of optimization variables corresponding to the simulation result with the optimal optimization target is selected from multiple numerical simulation results to serve as an optimization scheme for designing the semi-open type fuel centrifugal pump impeller. According to the method, the blade optimization scheme can be rapidly designed.

Description

Technical Field

[0001] The invention relates to the technical field of semi-open aviation fuel centrifugal pump impeller design, and in particular to a design method and system for a semi-open fuel centrifugal pump impeller. Background Art

[0002] As one of the important energy equipment, centrifugal pumps have been widely used in many industrial fields. Due to its large flow range, strong pressure boosting ability, reliable and stable continuous working ability, the fuel centrifugal pump can be used as a pre-stage boost pump or afterburner pump in the fuel system of an aircraft engine to supply sufficient power to the combustion chamber. Its performance seriously affects the working state and performance of the engine. As aircraft engines face increasingly harsh working environments, the working boundaries of aviation fuel centrifugal pumps vary more widely, the working environment is more severe, and its flow problems are more prominent. It is necessary to seek a design method that is more in line with its flow laws, and the integrated impeller design is one of the important key technologies.

[0003] In the prior art, in the field of centrifugal pump impeller optimization design, some researchers have used Bezier curves and linear functions to control the distribution of blade circumferential angles and the law of stacking changes under the Matlab platform, combined with the artificial fish swarm algorithm for optimization. Some researchers have conducted multi-objective optimization design and simulation research based on loss models and sequential quadratic programming algorithm SQP. Some researchers have taken improving hydraulic efficiency and cavitation performance as the goal, while taking the elimination of the hump of the performance curve and ensuring that the model pump is not overloaded as constraints, and constructed a mathematical optimization model to optimize the efficiency and cavitation performance of the centrifugal pump. Some researchers have constructed a Kriging proxy model based on Latin hypercube sampling to optimize the design of marine double-suction centrifugal pump impellers. Some researchers have used orthogonal experimental methods to optimize the design of deep well pump impellers.

[0004] In summary, although the existing technology uses Bezier curves to control parameters such as blade profiles to achieve blade control, most of them require the blade coordinate points to be exported to algorithm software, such as using algorithms in Matlab to control blades. This method is more cumbersome when more samples are required, resulting in a long time-consuming and extremely large amount of calculation in the early steps of computational fluid dynamics. Therefore, how to quickly design an optimization solution for blades is an important issue that needs to be solved urgently. Summary of the invention

[0005] The embodiment of the present invention provides a design method and system for a semi-open fuel centrifugal pump impeller, which can solve the problem in the prior art that it is impossible to quickly design an optimization solution for blades.

[0006] An embodiment of the present invention provides a method for designing a semi-open fuel centrifugal pump impeller, comprising the following steps: Select the efficiency and head of the semi-open fuel centrifugal pump as the optimization objectives, and determine the optimization variables that affect the optimization objectives; among them, the optimization variables include: the profiles of the impeller hub and shroud in the axial projection diagram, the blade thickness, and the parameters of the blade camber line; Use the Latin hypercube sampling method to design multiple sets of sample data corresponding to the optimization variables; establish a semi-open fuel centrifugal pump impeller model based on the sample data corresponding to each set of optimization variables and conduct numerical simulations to obtain the values of the optimization objectives corresponding to the sample data of each set of optimization variables; use each set of optimization variables and the values of the optimization objectives corresponding to the sample data of each set of optimization variables as the performance data of the centrifugal pump, and establish a database; Use the database to train the surrogate model to predict the optimization objectives and obtain the prediction model; use the multi-objective genetic optimization algorithm to optimize the optimization objectives predicted by the prediction model to obtain multiple sets of optimization variables that meet the optimization objectives; conduct numerical simulations on the multiple sets of optimization variables, and select a set of optimization variables corresponding to the simulation result with the optimal optimization objective from the multiple numerical simulation results as the optimization scheme for designing the semi-open fuel centrifugal pump impeller.

[0007] Furthermore, the design method of the semi-open fuel centrifugal pump impeller further includes: performing a flow field analysis based on the optimization data in the optimization scheme to evaluate the optimization results.

[0008] Furthermore, the specific steps of using the multi-objective genetic optimization algorithm to optimize the optimization objectives predicted by the prediction model include: using the multi-objective genetic optimization algorithm NSGA-II to optimize the optimization objectives until the preset termination conditions are met to obtain an approximate Pareto solution set; searching for the optimization scheme on the Pareto front of the approximate Pareto solution set.

[0009] Furthermore, the specific steps of determining the optimization variables that affect the optimization objectives include: Perform reverse processing on the three-dimensional model of the known semi-open fuel centrifugal pump impeller to obtain the impeller flow passage; Obtain the control points for controlling the blade shape and size according to the impeller flow passage; According to the control points, use the model design tool to generate a parametric model similar to the three-dimensional model of the known semi-open fuel centrifugal pump impeller, which can realize the parameterization of the front and rear profiles of the blade, the blade camber line, and the blade thickness by Bezier curves; According to the parametric model, use sensitivity analysis to determine the influence degree of the parameters in the model on the optimization objectives, and determine the parameters with a large influence on the optimization objectives as the optimization variables according to the influence degree.

[0010] An embodiment of the present invention provides a design system for a semi-open fuel centrifugal pump impeller, including: A parameter acquisition module, which is used to select the efficiency and head of a semi-open type fuel centrifugal pump as optimization objectives, and determine optimization variables that affect the optimization objectives; wherein, the optimization variables include: the profiles of the impeller hub and shroud on the axial projection drawing, the blade thickness, and the parameters of the blade camber line. A database establishment module, which is used to design sample data corresponding to multiple groups of optimization variables by using the Latin hypercube sampling method; establish a semi-open type fuel centrifugal pump impeller model according to the sample data corresponding to each group of optimization variables and conduct numerical simulations to obtain the optimization objective values corresponding to the sample data corresponding to each group of optimization variables; use each group of optimization variables and the optimization objective values corresponding to the sample data corresponding to each group of optimization variables as the centrifugal pump performance data, and establish a database. A scheme acquisition module, which is used to use the database to train a surrogate model to predict the optimization objective and obtain a prediction model; perform optimization on the optimization objective predicted by the prediction model through a multi-objective genetic optimization algorithm to obtain multiple groups of optimization variables that meet the optimization objective; conduct numerical simulations on the multiple groups of optimization variables, and select a group of optimization variables corresponding to the simulation result with the optimal optimization objective from multiple numerical simulation results as the optimization scheme for designing the semi-open type fuel centrifugal pump impeller.

[0011] The embodiment of the present invention provides a design method and system for a semi-open type fuel centrifugal pump impeller. Compared with the prior art, its beneficial effects are as follows: Perform Latin hypercube sampling on the optimization variables, and establish a semi-open type fuel centrifugal pump impeller model according to the sampling results, so as to simulate and obtain the optimization objective values in the semi-open type fuel centrifugal pump impeller model. Use each group of optimization variables and the optimization objective values corresponding to the sample data corresponding to each group of optimization variables as the centrifugal pump performance data, and establish a database. Train a surrogate model through the database to predict the optimization objective and obtain a prediction model. Perform optimization on the optimization objective predicted by the prediction model through a multi-objective genetic optimization algorithm to obtain multiple groups of optimization variables that meet the optimization objective; conduct numerical simulations on the multiple groups of optimization variables, and select a group of optimization variables corresponding to the simulation result with the optimal optimization objective from multiple numerical simulation results as the optimization scheme for designing the semi-open type fuel centrifugal pump impeller. This method can directly obtain the optimization objective through a group of optimization variables, and realizes the rapid design of the blade optimization scheme. Description of the Drawings

[0012] Figure 1 It is an integrated blade model after reverse modeling of a design method for a semi-open type fuel centrifugal pump impeller provided by an embodiment of the present invention. Figure 2 It is the control points of the impeller hub and shroud of a design method for a semi-open type fuel centrifugal pump impeller provided by an embodiment of the present invention. Figure 3 It is a schematic diagram of the blade camber line and related parameters of a design method for a semi-open type fuel centrifugal pump impeller provided by an embodiment of the present invention. Figure 4 The blade thickness control points and coordinates for the design method of a semi-open fuel centrifugal pump impeller provided by an embodiment of the present invention. Figure 5 The impeller optimization workflow diagram for the design method of a semi-open fuel centrifugal pump impeller provided by an embodiment of the present invention. Detailed implementation manners

[0013] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings. Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0014] An embodiment of the present invention provides a design method for a semi-open fuel centrifugal pump impeller, including the following steps: Step 1: Select the efficiency and head of the semi-open fuel centrifugal pump as the optimization objectives, and determine the optimization variables that affect the optimization objectives.

[0015] Step 2: Use the Latin hypercube sampling method to design multiple sets of sample data corresponding to the optimization variables; establish a semi-open fuel centrifugal pump impeller model based on each set of sample data corresponding to the optimization variables and perform numerical simulations to obtain the optimization objective values corresponding to each set of sample data corresponding to the optimization variables; take each set of optimization variables and the optimization objective values corresponding to each set of sample data corresponding to the optimization variables as the centrifugal pump performance data, and establish a database.

[0016] Step 3: Use the database to train a surrogate model to predict the optimization objectives and obtain a prediction model. Among them, the surrogate models include: orthogonal polynomial model, polynomial response surface model, radial basis function model, and Kriging model. Use the multi-objective genetic optimization algorithm to optimize the optimization objectives predicted by the prediction model to obtain multiple sets of optimization variables that meet the optimization objectives; perform numerical simulations on the multiple sets of optimization variables, and select a set of optimization variables corresponding to the simulation result with the optimal optimization objective from the multiple numerical simulation results as the optimization scheme for designing the semi-open fuel centrifugal pump impeller.

[0017] The corresponding solutions for the above steps are as follows: (1) Select variables according to the optimization objectives.

[0018] According to the design requirements of the semi-open centrifugal pump, after initially selecting the optimization target parameters and based on the establishment of the parametric model of the blade, through sensitivity calculation and analysis, the geometric parameters that have a greater impact on the optimization target are selected as the final optimization variables; the optimization target refers to the efficiency and head of the centrifugal pump at the design flow rate. The optimization variables include the profile parameters of the impeller hub and shroud in the axial projection diagram, the blade thickness, and the parameters of the blade backbone line.

[0019] After completing the establishment of the parametric model, it is imported into the mesh generation software Turbogrid to generate high-quality hexahedral meshes and perform mesh independence verification. Since parametric optimization work requires a large number of experimental design models to be calculated to ensure the accuracy of the results, before calculation, in order to reduce the number of meshes as much as possible on the premise of ensuring the calculation accuracy, mesh independence verification is carried out in advance, and a suitable mesh size is selected as the mesh generation standard for subsequent parametric optimization calculations.

[0020] (2) Experimental design.

[0021] The Latin square hypercube sampling design experimental method is used to establish experimental samples for each optimization variable, and these data are integrated as the database for training the surrogate model; according to the geometric parameters given in each experimental scheme in the database, the original parametric model of the aviation fuel centrifugal pump is modified in the impeller design software to generate the corresponding aviation fuel centrifugal pump model; numerical simulations are carried out on the aviation fuel centrifugal pump models corresponding to each experimental scheme to obtain the optimization target values of different samples and obtain the simulation results of all experimental schemes.

[0022] (3) Construct a surrogate model.

[0023] The relationships between input variables and output variables are established using different surrogate model algorithms, the accuracy of each surrogate model is verified, and the one with the best performance is selected as the prediction model.

[0024] (4) Multi-objective search for optimization solutions.

[0025] The multi-objective genetic optimization algorithm is used to optimize the optimization target to obtain the optimization solution. This invention is for multi-objective optimization, and the algorithm will continue to iterate until the preset termination conditions are met, that is, the quality of the solution reaches the established standard. When the termination conditions are met, the individuals retained in the last environmental selection will constitute an approximate Pareto solution set. Designers should find suitable optimization solutions in the Pareto front according to actual needs.

[0026] (5) Confirm the optimization results.

[0027] Numerical simulation and calculation are carried out on the optimization scheme. The optimization algorithm obtains a combination of performance parameters, taking into account both hydraulic efficiency and head. The performance parameter combinations with better hydraulic efficiency and head are screened out, and the group with the highest comprehensive parameter of hydraulic efficiency and head is selected as the final optimization scheme. The flow field of the aviation fuel centrifugal pump with the optimal design scheme is analyzed, and the performance before and after optimization is compared to confirm the optimization results.

[0028] In part (1), first, the optimization objectives are determined according to actual requirements. In this invention, the efficiency and head of the designed flow rate are taken as the optimization objectives at the same time; first, the reverse processing operation is carried out on the three-dimensional impeller model of the centrifugal pump using design software. Import the impeller parameterization tool to realize the parameterization of the profile line parameters, blade thickness, and blade backbone line of the impeller hub and shroud on the axial projection drawing.

[0029] In part (2), the Latin hypercube sampling design is used to sample the optimization variables. This method has uniform sampling and good orthogonality. Different centrifugal pump impeller models are established according to the sampling data, and the centrifugal pumps equipped with different centrifugal pump impellers are simulated and calculated to obtain the centrifugal pump performance data as the test sample point database.

[0030] In part (3), different surrogate model algorithms are used to establish the relationship between input variables and output variables. Several surrogate models are compared at the theoretical level, and the relationship between input variables and output variables is established using each method in turn, and the model with the best performance is selected as the prediction model.

[0031] In part (4), the multi-objective genetic optimization algorithm is used to optimize the optimization objectives to obtain the optimization scheme; this invention is for multi-objective optimization, and the algorithm will continue to iterate until the preset termination conditions are met, that is, the quality of the solution reaches the established standard. When the termination conditions are met, the individuals retained in the last environmental selection will constitute an approximate Pareto solution set. Designers should find a suitable optimization scheme in the Pareto front according to actual requirements.

[0032] In summary, the integrated impeller optimization method proposed by this invention greatly reduces the optimization threshold. The impeller parameterization design method based on the Bezier curve can effectively reduce the number of tests in the development process of the centrifugal pump, use the parameterized curve to realize the rapid control of the blade profile line, provide a rich data basis for the optimization design, and can effectively improve the design speed and accuracy.

[0033] An embodiment of the present invention provides a design system for a semi-open fuel centrifugal pump impeller, including: A parameter acquisition module, which is used to select the efficiency and head of the semi-open fuel centrifugal pump as the optimization objectives and determine the optimization variables that affect the optimization objectives; among them, the optimization variables include: the profile line, blade thickness, and parameters of the blade backbone line of the impeller hub and shroud on the axial projection drawing.

[0034] A database establishment module is used to design sample data corresponding to multiple groups of optimization variables by using the Latin hypercube sampling method; establish a semi-open type fuel centrifugal pump impeller model based on the sample data corresponding to each group of optimization variables and conduct numerical simulations to obtain the optimization target values corresponding to the sample data of each group of optimization variables; use each group of optimization variables and the optimization target values corresponding to the sample data of each group of optimization variables as centrifugal pump performance data and establish a database.

[0035] A solution acquisition module is used to train a surrogate model using the database to predict the optimization target and obtain a prediction model; optimize the optimization target predicted by the prediction model through a multi-objective genetic optimization algorithm to obtain multiple groups of optimization variables that meet the optimization target; conduct numerical simulations on multiple groups of optimization variables and select a group of optimization variables corresponding to the simulation result with the optimal optimization target from multiple numerical simulation results as the optimization solution for designing the semi-open type fuel centrifugal pump impeller.

[0036] A specific embodiment is as follows: According to the design requirements of the semi-open centrifugal pump, select the optimization target parameters. The optimization target refers to the efficiency and head of the centrifugal pump design flow rate. Determine the optimization targets according to the requirements, including the profiles of the impeller hub and shroud on the axial projection diagram, the blade thickness, and the parameters of the blade backbone line, and then make a preliminary selection of the geometric parameters to be optimized and their ranges.

[0037] Use the BladeEditor function of the enhanced blade geometry modeling in the 3D modeling module DesignModeler in ANSYS Workbench to perform reverse processing operations on the 3D impeller model of the centrifugal pump, such as Figure 1 shown. First, generate the Flowpath impeller flow channel, then generate the control points ExportPoints of the long and short blades, and then complete the reverse design.

[0038] Import the interactive turbomachinery blade design tool BladeGen to implement the Bezier curve for the profile parameters of the impeller hub and shroud on the axial projection diagram, the blade thickness, and the parameters of the blade backbone line, and complete the generation of the parametric model.

[0039] Take 3 control points for the shroud contour line and 3 control points for the impeller hub contour segment, as Figure 2 shown, both are determined by the five-point fourth-order Bezier curve. Therefore, there are a total of 12 optimization parameters for the impeller hub and shroud.

[0040] Select 6 control points corresponding to the circumferential angles of two streamlines at span = 0 and span = 1 positions, as Figure 3 shown, which are determined by the five-point fourth-order Bezier curve, that is, 12 optimization parameters.

[0041] Select the thickness of the streamline control impeller blade at the position where span = 0.5, as Figure 4 shown, which is determined by a five-point and fourth-degree Bezier curve, with 6 optimization parameters.

[0042] A total of 30 optimization parameters are initially determined.

[0043] Import the model in Bladegen into Turbogrid to automatically generate high-quality hexahedral meshes, and use Meshing to generate the meshes of other components (volute, inlet section). Import the divided meshes into the CFX or Fluent numerical simulation software, and perform transient numerical simulation calculations on the centrifugal pump under rated conditions to obtain the numerical simulation results, and obtain the efficiency and head under this condition.

[0044] On the basis of establishing the parametric model of the blade, select the parameters with a greater impact on the optimization target as the optimization variables through sensitivity calculation; optimize the model through the parameter optimization software OptiSLang carried by the simulation software Workbench platform, and the complete workflow is as Figure 5 . Based on the sensitivity analysis, obtain the optimal response design parameters as the final optimization parameters. After converting the research object into a mathematical model, assume that the model has n parameters and has a functional relationship y = f ( x 1, x 2,..., x n )), on the premise of ensuring that all parameters except x i remain unchanged, let this parameter take values within its possible variation range. The basic idea is to observe the change of the system output quantity by changing the value of a certain parameter one by one, so as to calculate the sensitivity coefficient of this parameter. According to the calculated sensitivity coefficient, it can be judged which input parameters have a greater impact on the system output, so as to provide a basis for subsequent optimization, adjustment or decision-making.

[0045] Using the experimental design method provided by the Design Exploration module in ANSYS Workbench, in the Toolbox of Workbench, select Sensitivity under OptiSLang to enter parametric design, and select the sampling method in DOE. For this optimization method, the research adopts the Latin square hypercube sampling design test method to generate sample data for each optimization variable according to the experimental design. The number of samples is generally taken as 2( n +1)( n +2) groups ( n(the number of final optimized parameters after sensitivity analysis), different centrifugal pump impeller models are established based on the sampling data, and the centrifugal pumps equipped with different centrifugal pump impellers are simulated to obtain the centrifugal pump performance data as the database.

[0046] The surrogate model is used to predict the target optimized parameters of the centrifugal pumps with different impellers. First, different surrogate models are trained using the database. A variety of surrogate models provided by the ANSYS OptiSLang platform are used to meet different research needs. These include the Orthogonal Polynomial Model (OPM), the Response Surface Model (RSM), the Radial Basis Function (RBF) model, and the Kriging model. In engineering research, to ensure the accuracy of the surrogate model and effectively control the time cost, the RSM of order 1 to 4 can be selected as the surrogate model. This is because the low-order RSM can better capture the system behavior, and at the same time, the computational complexity is relatively low, which is suitable for quickly evaluating the design scheme. The RBF can flexibly handle non-linear relationships and still maintain good prediction performance when the number of samples is limited. After comparing the performance of each surrogate model in the present invention, the RSM model with better performance is selected as the final prediction model.

[0047] The NSGA-II algorithm is used to perform multi-objective optimization on the head and efficiency under the design conditions. The multi-objective genetic optimization algorithm is used to optimize the optimization objectives to obtain the optimization scheme. The present invention is for multi-objective optimization, and the algorithm will continue to iterate until the preset termination condition is met, that is, the quality of the solution reaches the established standard. When the termination condition is satisfied, the individuals retained in the last environmental selection will form an approximate Pareto solution set. Designers should find a suitable optimization scheme in the Pareto front according to actual needs.

[0048] Numerical simulation and calculation are carried out on the optimization scheme. The optimization algorithm obtains the combination of performance parameters, taking into account the hydraulic efficiency and the head, screens out the performance parameter combinations with better hydraulic efficiency and head, and selects the group with the highest hydraulic efficiency as the final optimization scheme. After obtaining the optimization scheme, the finally obtained optimization data is substituted into the original model, and its simulation calculation is carried out, and the results of the surrogate model and the simulation calculation are compared to verify the accuracy of the results. The flow field analysis of the fuel centrifugal pump with the optimal design scheme is carried out to compare the performance before and after optimization and confirm the optimization results.

[0049] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several variations and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A design method for a semi-open fuel centrifugal pump impeller, characterized in that, It includes the following steps: Select the efficiency and head of the semi-open fuel centrifugal pump as the optimization objectives, and determine the optimization variables that affect the optimization objectives; among them, the optimization variables include: the profiles of the impeller hub and shroud in the axial projection view, the blade thickness, and the parameters of the blade camber line; Use the Latin hypercube sampling method to design multiple sets of sample data corresponding to the optimization variables; establish a semi-open fuel centrifugal pump impeller model based on each set of sample data corresponding to the optimization variables and conduct numerical simulations to obtain the values of the optimization objectives corresponding to each set of sample data; take each set of optimization variables and the values of the optimization objectives corresponding to each set of sample data as the centrifugal pump performance data, and establish a database; Use the database to train the surrogate model to obtain a prediction model; optimize the optimization objectives predicted by the prediction model through the multi-objective genetic optimization algorithm to obtain multiple sets of optimization variables that meet the optimization objectives; Conduct numerical simulations on multiple sets of optimization variables, and select a set of optimization variables corresponding to the simulation result with the optimal optimization objective from multiple numerical simulation results as the optimization scheme for designing the semi-open fuel centrifugal pump impeller.

2. The design method of a semi-open fuel centrifugal pump impeller according to claim 1, characterized in that, The design method of the semi-open fuel centrifugal pump impeller further includes: According to the optimization data in the optimization scheme, conduct a flow field analysis to evaluate the optimization results.

3. The design method of a semi-open fuel centrifugal pump impeller according to claim 1, characterized in that The specific steps of optimizing the optimization objectives predicted by the prediction model through the multi-objective genetic optimization algorithm include: Use the multi-objective genetic optimization algorithm NSGA-II to optimize the optimization objectives until the preset termination conditions are met to obtain an approximate Pareto solution set; Search for the optimization scheme on the Pareto front of the approximate Pareto solution set.

4. The design method of a semi-open fuel centrifugal pump impeller according to claim 1, characterized in that, The specific steps of determining the optimization variables that affect the optimization objectives include: Perform reverse processing on the three-dimensional model of the known semi-open fuel centrifugal pump impeller to obtain the impeller flow passage; According to the impeller flow passage, obtain the control points for controlling the blade shape and size; According to the control points, use the model design tool to generate a parametric model similar to the three-dimensional model of the known semi-open fuel centrifugal pump impeller, which can realize the parameterization of the front and rear profiles of the blade, the blade camber line, and the blade thickness by Bezier curves; According to the parametric model, use sensitivity analysis to determine the influence degree of the parameters in the model on the optimization objectives, and determine the parameters with a large influence on the optimization objectives as the optimization variables according to the influence degree.

5. A design system for a semi-open fuel centrifugal pump impeller, characterized in that, It includes: A parameter acquisition module, which is used to select the efficiency and head of the semi-open fuel centrifugal pump as the optimization objectives, and determine the optimization variables that affect the optimization objectives; among them, the optimization variables include: the profiles of the impeller hub and shroud in the axial projection view, the blade thickness, and the parameters of the blade camber line; A database establishment module, which is used to use the Latin hypercube sampling method to design multiple sets of sample data corresponding to the optimization variables; establish a semi-open fuel centrifugal pump impeller model based on each set of sample data corresponding to the optimization variables and conduct numerical simulations to obtain the values of the optimization objectives corresponding to each set of sample data; take each set of optimization variables and the values of the optimization objectives corresponding to each set of sample data as the centrifugal pump performance data, and establish a database; A solution acquisition module is used to train an agent model using a database to predict an optimization objective and obtain a prediction model; perform optimization on the optimization objective predicted by the prediction model through a multi-objective genetic optimization algorithm to obtain multiple groups of optimization variables that meet the optimization objective; perform numerical simulations on the multiple groups of optimization variables, and select a group of optimization variables corresponding to the simulation result with the optimal optimization objective from multiple numerical simulation results as the optimization solution for designing the impeller of a semi-open fuel centrifugal pump.

Images