Charging pile axial flow fan blade parameter optimization method based on genetic algorithm

Abstract

The invention discloses a charging pile axial flow fan blade parameter optimization method based on a genetic algorithm, and the method comprises the steps: extracting the geometrical shape of an existing blade, calculating a performance curve of an existing fan structure, and carrying out the verification through an experiment; drawing a hub line and a wheel cover line in a meridian plane; reconstructing a three-dimensional model of the moving blade; keeping the molded lines of the constructed hub and axle unchanged, widening the molded lines of the front and rear edges of the meridian plane blade to enable the width to be matched with the axial height of the blade, and constructing a single flow channel; 5, performing three-dimensional calculation by using the obtained three-dimensional moving blade model, and verifying whether data features are matched or not; step 6, establishing a meta-model; performing genetic algorithm multi-target optimization; according to the method, the genetic algorithm is utilized, and the axial flow fan blade with the minimum fan power and the maximum static pressure efficiency is rapidly and accurately obtained; in addition, the blade of the axial flow fan is researched through parameterization, and the blade with changed geometric parameters can be verified more easily.

Description

Technical Field

[0001] The present invention relates to the technical field of optimization of axial flow fan blades for charging piles, and in particular to a method for optimizing the parameters of axial flow fan blades for charging piles based on a genetic algorithm. Background Art

[0002] The axial flow fan inside the charging pile is characterized by the airflow direction being in the same direction as the axis of the fan blades, a high wind pressure coefficient and a large flow coefficient. It is also very convenient to install, making it very suitable for the internal heat dissipation needs of the charging pile. The fan blades are one of the important factors in optimizing the performance of the axial flow fan, but the design optimization research of the axial flow fan blades is still relatively insufficient.

[0003] The design optimization of axial fan blades is difficult and the workload is large due to the complexity of blade geometry. How to quickly perform a large amount of blade geometry optimization work is the key to the development of axial fan blade optimization technology. There are two unreasonable aspects in the current axial fan blade parameterization method: First, due to the complexity of blade geometry, the current axial fan blade optimization is very cumbersome and labor-intensive, and it is difficult to quickly obtain the best axial fan blade design selection. Secondly, when using the current axial fan blade geometry feature method to perform blade optimization work, it is difficult to conveniently adjust the axial fan blades, which affects the work of verifying the effect of the changed axial fan blades.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] The present invention provides a charging pile axial flow fan blade parameter optimization method based on genetic algorithm. The genetic algorithm is used to quickly and accurately obtain the axial flow fan blade with the minimum fan power and the maximum static pressure efficiency. The axial flow fan blade is studied by parameterization, which makes it easier to verify the blade with changed geometric parameters.

[0006] A method for optimizing blade parameters of an axial flow fan of a charging pile based on a genetic algorithm includes: Step 1: Import the blade structure of the axial flow fan of the charging pile into the full 3D modeling software to extract the blade parameters, where the fan rotation axis is the global Z axis in the 3D coordinate system, and extract the end face of the blade close to the rotation axis and the end face close to the fan casing; rotate the extracted end face and cut it into four parts using the global YZ and ZX planes respectively, retain the hub and wheel cover rotation surface of the global XY positive half axis part, create a new sketch facing the global ZX plane, extract the lines mapped on the new sketch of the retained hub and wheel cover rotation surface as the hub and wheel cover lines, and calculate the performance curve of the existing fan structure and verify it with the experiment; Step 2: Based on the blade structure parameters of the charging pile axial flow fan blade structure, use the blade modeling software and adopt the following blade shaping method: draw the hub line and wheel cover line in the meridian plane, and use Bezier curve Construct the stacking line of the blade contour to generate the pressure surface and suction surface profiles at the blade hub and wheel cover sections, where P(t) is the coordinate of any point of the parameterized Bezier curve; n is the order of the parameterized Bezier curve; i is the current order, i=0, 1, 2, . . . ; P i is the position vector of each vertex; B i,n (t) is the Bernstein basis function, ; t is the curve parameter variable, ; Step 3: Based on the extracted control points of the blade hub and wheel cover, re-import the BladeEditor 3D software to automatically generate a 3D model of the rotor blade; Step 4: Keep the constructed hub line and wheel cover line unchanged, widen the meridian blade leading and trailing edge profiles so that their width can match the blade axial height, and construct a single flow channel; Step 5, performing 3D calculation using the 3D model of the moving blade, if the calculated flow distribution and pressure distribution data match the performance curve characteristics calculated in step 1, it proves that the blade parameter extraction is successful, if not, return to step 2 to step 5 until the flow distribution and pressure distribution data match the performance curve characteristics; Step 6: Using the extracted blade parameters changing with the blade relative thickness M%, the advanced Latin hypercube method is used to establish a sample space within the restricted range, and the output value of the established sample data is solved. Based on the extracted control points of the blade hub and wheel cover, the blade is re-imported into the BladeEditor 3D software to automatically generate a 3D model of the moving blade to establish a metamodel; Step seven, based on the meta-model, using its optimal structural parameters as the initial values ​​of genetic algorithm optimization, applying the response surface model, and using the optimization module to perform genetic algorithm multi-objective optimization, while reducing the fan power, improving the fan static pressure efficiency, improving the fan aerodynamic performance, and thus increasing the heat dissipation of the charging pile.

[0007] In the method for optimizing blade parameters of an axial flow fan for a charging pile based on a genetic algorithm, the full three-dimensional modeling software is Fluent, and the blade modeling software is BladeEditor.

[0008] In the method for optimizing the blade parameters of the charging pile axial flow fan based on a genetic algorithm, one blade number is retained in the hub line and the wheel cover line drawn in the meridian plane, the axial chord length remains unchanged, the leading edge is outlined with a square section, and the trailing edge is outlined with a section with an ellipse ratio of 1000.

[0009] In the method for optimizing the blade parameters of an axial flow fan for a charging pile based on a genetic algorithm, in step 2, the hub wheel cover lines formed by the stacked lines of the blade contours are the lines obtained by offsetting the blade root by 3% relative to the center axis of the hub and the blade tip by 3% relative to the center axis of the wheel cover.

[0010] In the method for optimizing the blade parameters of the charging pile axial flow fan based on genetic algorithm, in step 6, the relative thickness of the blade , which is the percentage of the thickness of the blade at a certain position relative to the chord length, where x is the distance from the leading edge to a specific position on the blade; t(x) is the thickness of the blade at position x; and C is the chord length of the blade.

[0011] In the method for optimizing the blade parameters of the charging pile axial flow fan based on genetic algorithm, in step six, the extracted blade parameters include: blade angle at 0% of the blade hub, blade angle at 25% of the blade hub, blade angle at 50% of the blade hub, blade angle at 75% of the blade hub, blade angle at 100% of the blade hub, blade normal layer thickness at 0% of the blade hub, blade normal layer thickness at 25% of the blade hub, blade normal layer thickness at 50% of the blade hub, blade normal layer thickness at 75% of the blade hub 20 blade parameters including thickness, blade normal layer thickness at 100% of blade hub, blade angle at 0% of blade wheel shroud, blade angle at 25% of blade wheel shroud, blade angle at 50% of blade wheel shroud, blade angle at 75% of blade wheel shroud, blade angle at 100% of blade wheel shroud, blade normal layer thickness at 0% of blade wheel shroud, blade normal layer thickness at 25% of blade wheel shroud, blade normal layer thickness at 50% of blade wheel shroud, blade normal layer thickness at 75% of blade wheel shroud and blade normal layer thickness at 100% of blade wheel shroud.

[0012] In the method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm, in step six, the sample output value to be solved refers to the static pressure efficiency and power of the fan.

[0013] In the method for optimizing the blade parameters of the axial flow fan of a charging pile based on a genetic algorithm, in step 6, the metamodel evaluation criteria are: prognosis coefficient To evaluate the quality of the established response surface model; is the sum of squared prediction errors, which are estimated based on cross-validation; is the total change, .

[0014] In the method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm, in step seven, the objective function is to minimize the fan power and maximize the static pressure efficiency.

[0015] In the method for optimizing blade parameters of an axial flow fan of a charging pile based on a genetic algorithm, the axial flow fan of the charging pile is arranged in a charging station.

[0016] Compared with the prior art, the present invention has the following advantages: the method for optimizing the parameters of the axial flow fan blades of a charging pile based on a genetic algorithm described in the present invention utilizes a genetic algorithm to quickly and accurately obtain the axial flow fan blades with the minimum fan power and the maximum static pressure efficiency; and the axial flow fan blades are studied by parameterization, which makes it easier to verify the blades with changed geometric parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the detailed description of the preferred specific embodiments below, various other advantages and benefits of the present invention will become clear to those of ordinary skill in the art. The drawings in the specification are only for the purpose of illustrating the preferred embodiments and are not considered to be limitations of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work. Moreover, the same reference numerals are used to represent the same components throughout the drawings.

[0018] In the attached picture: Figure 1 It is a schematic diagram of the parameter optimization process of the axial flow fan blades of a charging pile based on a genetic algorithm; Figure 2 It is a schematic diagram of the meridian plane of a single flow channel of a blade; Figure 3 It is a schematic diagram of blade three-dimensional model parameter extraction; Figure 4 It is based on the NSGA-II multi-objective optimization Pareto diagram; Figure 5 This is a schematic diagram comparing blade angles before and after optimization; Figure 6 It is a schematic diagram comparing the three-dimensional models of blades before and after optimization.

[0019] The present invention is further explained below in conjunction with the accompanying drawings and embodiments. DETAILED DESCRIPTION

[0020] The specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the specific embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0021] It should be noted that certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that technicians may use different nouns to refer to the same component. This specification and claims do not use the difference in nouns as a way to distinguish components, but use the difference in the functions of the components as the criterion for distinction. As mentioned throughout the specification and claims, "including" or "comprising" is an open term, so it should be interpreted as "including but not limited to". The subsequent description of the specification is a preferred embodiment of the present invention, but the description is based on the general principles of the specification and is not intended to limit the scope of the present invention. The scope of protection of the present invention shall be determined by the attached claims.

[0022] To facilitate understanding of the embodiments of the present invention, further explanation will be given below by taking specific embodiments as examples in conjunction with the accompanying drawings, and each of the accompanying drawings does not constitute a limitation on the embodiments of the present invention.

[0023] like Figures 1 to 6 As shown, the parameter optimization method of the charging pile axial flow fan blade based on genetic algorithm includes the following steps: Step 1: Import the blade structure of the axial flow fan of the charging pile into the full 3D modeling software to extract the blade parameters, where the fan rotation axis is the global Z axis in the 3D coordinate system, and extract the end face of the blade close to the rotation axis and the end face close to the fan casing; rotate the extracted end face and cut it into four parts using the global YZ and ZX planes respectively, retain the hub and wheel cover rotation surface of the global XY positive half axis part, create a new sketch facing the global ZX plane, extract the lines mapped on the new sketch of the retained hub and wheel cover rotation surface as the hub and wheel cover lines, and calculate the performance curve of the existing fan structure and verify it with the experiment; Step 2: Based on the blade structure parameters of the charging pile axial flow fan blade structure, use the blade modeling software and adopt the following blade shaping method: draw the hub line and wheel cover line in the meridian plane, and use Bezier curve Construct the stacking line of the blade contour to generate the pressure surface and suction surface profiles at the blade hub and wheel cover sections, where P(t) is the coordinate of any point of the parameterized Bezier curve; n is the order of the parameterized Bezier curve; i is the current order, i=0, 1, 2, . . . ; P i is the position vector of each vertex; B i,n (t) is the Bernstein basis function, ; t is the curve parameter variable, ; Step 3: Based on the extracted control points of the blade hub and wheel cover, re-import the BladeEditor 3D software to automatically generate a 3D model of the rotor blade; Step 4: Keep the constructed hub line and wheel cover line unchanged, widen the meridian blade leading and trailing edge profiles so that their width can match the blade axial height, and construct a single flow channel; Step 5, performing 3D calculation using the 3D model of the moving blade, if the calculated flow distribution and pressure distribution data match the performance curve characteristics calculated in step 1, it proves that the blade parameter extraction is successful, if not, return to step 2 to step 5 until the flow distribution and pressure distribution data match the performance curve characteristics; Step 6: Using the extracted blade parameters changing with the blade relative thickness M%, the advanced Latin hypercube method is used to establish a sample space within the restricted range, and the output value of the established sample data is solved. Based on the extracted control points of the blade hub and wheel cover, the blade is re-imported into the BladeEditor 3D software to automatically generate a 3D model of the moving blade to establish a metamodel; Step seven, based on the meta-model, using its optimal structural parameters as the initial values ​​of genetic algorithm optimization, applying the response surface model, and using the optimization module to perform genetic algorithm multi-objective optimization, while reducing the fan power, improving the fan static pressure efficiency, improving the fan aerodynamic performance, and thus increasing the heat dissipation of the charging pile.

[0024] In the preferred implementation of the method for optimizing blade parameters of an axial flow fan of a charging pile based on a genetic algorithm, the full three-dimensional modeling software is Fluent, and the blade modeling software is BladeEditor.

[0025] In a preferred implementation of the method for optimizing the blade parameters of an axial flow fan for a charging pile based on a genetic algorithm, one blade number is retained in the hub line and the wheel cover line drawn in the meridian plane, the axial chord length remains unchanged, the leading edge is outlined with a square section, and the trailing edge is outlined with a section with an ellipse ratio of 1000.

[0026] In a preferred implementation of the method for optimizing the blade parameters of an axial flow fan for a charging pile based on a genetic algorithm, in step two, the hub wheel cover lines formed by the blade contour stacking lines are the lines obtained by offsetting the blade root by 3% relative to the center axis of the hub and the blade tip by 3% relative to the center axis of the wheel cover.

[0027] In the preferred implementation of the method for optimizing the parameters of the axial flow fan blades of a charging pile based on a genetic algorithm, in step 6, the relative thickness of the blades , which is the percentage of the thickness of the blade at a certain position relative to the chord length, where x is the distance from the leading edge to a specific position on the blade; t(x) is the thickness of the blade at position x; and C is the chord length of the blade.

[0028] In a preferred implementation of the method for optimizing the blade parameters of the charging pile axial flow fan based on a genetic algorithm, in step six, the extracted blade parameters include: blade angle at 0% of the blade hub, blade angle at 25% of the blade hub, blade angle at 50% of the blade hub, blade angle at 75% of the blade hub, blade angle at 100% of the blade hub, blade normal layer thickness at 0% of the blade hub, blade normal layer thickness at 25% of the blade hub, blade normal layer thickness at 50% of the blade hub, blade normal layer thickness at 75% of the blade hub 20 blade parameters including normal layer thickness, blade normal layer thickness at 100% of blade hub, blade angle at 0% of blade wheel shroud, blade angle at 25% of blade wheel shroud, blade angle at 50% of blade wheel shroud, blade angle at 75% of blade wheel shroud, blade angle at 100% of blade wheel shroud, blade normal layer thickness at 0% of blade wheel shroud, blade normal layer thickness at 25% of blade wheel shroud, blade normal layer thickness at 50% of blade wheel shroud, blade normal layer thickness at 75% of blade wheel shroud and blade normal layer thickness at 100% of blade wheel shroud.

[0029] In the preferred implementation of the method for optimizing the blade parameters of the charging pile axial flow fan based on a genetic algorithm, in step six, solving the sample output value refers to the static pressure efficiency and power of the fan.

[0030] In the preferred implementation of the method for optimizing the parameters of the axial flow fan blades of a charging pile based on a genetic algorithm, in step 6, the metamodel evaluation criteria are: prognosis coefficient To evaluate the quality of the established response surface model; is the sum of squared prediction errors, which are estimated based on cross-validation; is the total change, .

[0031] In the preferred implementation of the method for optimizing the blade parameters of the charging pile axial flow fan based on a genetic algorithm, in step seven, the objective function is to minimize the fan power and maximize the static pressure efficiency.

[0032] In a preferred implementation of the method for optimizing blade parameters of an axial flow fan of a charging pile based on a genetic algorithm, the axial flow fan of the charging pile is arranged in a charging station.

[0033] In one embodiment, if Figure 1As shown in the figure, a parameter optimization process of the axial flow fan blade of a charging pile based on a genetic algorithm includes: based on the Bezier curve, the three-dimensional blade shape, chord length, and installation angle of the fan blade are parametrically defined, and the overall structural parameters of the fan such as the tip and root diameter and the number of blades are added to obtain 20 blade parameters. After obtaining the three-dimensional coordinate points, they are imported into BladeEditor for surface and solid modeling, and finally the hub, wheel cover and blade entities are merged to complete the modeling; sample points are collected in the established sample space using the optimal Latin hypercube test method to provide sufficient learning samples for establishing a response surface model, and parameter sensitivity analysis is performed to filter out parameters that have little influence on the target parameters to narrow the subsequent optimization space and increase the calculation speed; a genetic algorithm is used to perform multi-objective optimization with fan power and fan static pressure efficiency as target parameters to obtain a Pareto optimal solution set; In one embodiment, if Figure 2 As shown, constructing a single flow channel of a blade includes: extracting a three-dimensional model of a blade 2, outlining a meridian flow channel hub profile 3 and a wheel cover profile 4 of the blade 2 on the global ZX plane, closing the meridian flow channel with an inlet 1 and an outlet 5 in the same ZX plane, fitting the blade hub and wheel cover profiles with a 5th-order Bezier curve, and fitting the blade installation angle distribution curve with a 3rd-order Bezier curve for blade parameterized control; In one embodiment, if Figure 3 As shown, the extracted space control points of the hub and wheel cover profile of the blade three-dimensional model are used. The profiles at the wheel cover and the axle are used to generate three-dimensional blades along the stacking line. The leading and trailing edges of the blades are depicted by ellipses with a curvature of 1000. In one embodiment, if Figure 4 As shown in the figure, for multi-objective optimization problems, the various objectives are generally conflicting. When one sub-objective is improved, another sub-objective may be reduced. Based on the Pareto optimal solution set established by NSGA-II multi-objective optimization, it is necessary to coordinate and balance these design points between the two optimization objectives according to actual needs, and select the Pareto frontier non-inferior solution B that meets the needs. The following Table 1 is a comparison between the selected optimal solution and the initial value. It can be seen that the static pressure efficiency decreases by 5.9% and the required power decreases by 25.8%. It is proved that the proposed approximate model optimization method and process have important engineering application value; Table 1: Pareto optimal solution set Fan power (P / W) Static pressure efficiency Original Model 55.585888 0.34050566 Optimized model 41.2308 0.320366 In one embodiment, if Figure 5 As shown in the figure, by comparing the blade angles of the optimized model and the original model, it can be clearly seen that the hub near the trailing edge of the blade and the wheel cover near the leading edge have a great influence on the aerodynamic performance of the blade; In one embodiment, if Figure 6As shown in the figure, the three-dimensional model comparison before and after fan optimization is shown. By changing the blade center arc line, blade thickness and blade angle distribution at the blade hub and wheel cover, the fan power can be significantly reduced, laying the foundation for the rapid optimization design of the fan.

[0034] Although the embodiments of the present invention are described above in conjunction with the accompanying drawings, the present invention is not limited to the above specific embodiments and application fields, and the above specific embodiments are only illustrative and instructive, rather than restrictive. A person of ordinary skill in the art can also make many forms under the guidance of this specification and without departing from the scope of protection of the claims of the present invention, all of which belong to the protection of the present invention.

Claims

1. A method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm, characterized in that: The steps include: Step 1: Import the blade structure of the axial flow fan of the charging pile into the full 3D modeling software to extract the blade parameters, where the fan rotation axis is the global Z axis in the 3D coordinate system, and extract the end face of the blade close to the rotation axis and the end face close to the fan casing; rotate the extracted end face and cut it into four parts using the global YZ and ZX planes respectively, retain the hub and wheel cover rotation surface of the global XY positive half axis part, create a new sketch facing the global ZX plane, extract the lines mapped on the new sketch of the retained hub and wheel cover rotation surface as the hub and wheel cover lines, and calculate the performance curve of the existing fan structure and verify it with the experiment; Step 2: Based on the blade structure parameters of the charging pile axial flow fan blade structure, use the blade modeling software and adopt the following blade shaping method: draw the hub line and wheel cover line in the meridian plane, and use Bezier curve Construct the stacking line of the blade contour to generate the pressure surface and suction surface profiles at the blade hub and wheel cover sections, where P(t) is the coordinate of any point of the parameterized Bezier curve; n is the order of the parameterized Bezier curve; i is the current order, i=0, 1, 2, . . . ; P i is the position vector of each vertex; B i,n (t) is the Bernstein basis function, ; t is the curve parameter variable, ; Step 3: Based on the extracted control points of the blade hub and wheel cover, re-import the BladeEditor 3D software to automatically generate a 3D model of the rotor blade; Step 4: Keep the constructed hub line and wheel cover line unchanged, widen the meridian blade leading and trailing edge profiles so that their width can match the blade axial height, and construct a single flow channel; Step 5, performing 3D calculation using the 3D model of the moving blade, if the calculated flow distribution and pressure distribution data match the performance curve characteristics calculated in step 1, it proves that the blade parameter extraction is successful, if not, return to step 2 to step 5 until the flow distribution and pressure distribution data match the performance curve characteristics; Step 6: Using the extracted blade parameters changing with the blade relative thickness M%, the advanced Latin hypercube method is used to establish a sample space within the restricted range, and the output value of the established sample data is solved. Based on the extracted control points of the blade hub and wheel cover, the blade is re-imported into the BladeEditor 3D software to automatically generate a 3D model of the moving blade to establish a metamodel; Step seven, based on the meta-model, using its optimal structural parameters as the initial values ​​of genetic algorithm optimization, applying the response surface model, and using the optimization module to perform genetic algorithm multi-objective optimization, while reducing the fan power, improving the fan static pressure efficiency, improving the fan aerodynamic performance, and thus increasing the heat dissipation of the charging pile.

2. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1, characterized in that: The full 3D modeling software is Fluent, and the blade modeling software is BladeEditor.

3. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1, characterized in that: When drawing the hub line and wheel cover line in the meridian plane, the number of blades is retained, the axial chord length remains unchanged, the leading edge is outlined with a square section, and the trailing edge is outlined with a section with an ellipse ratio of 1000.

4. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1, characterized in that: In step 2, the hub shroud lines formed by the blade contour stacking lines are the lines obtained by offsetting the blade root by 3% relative to the hub center axis and the blade tip by 3% relative to the shroud center axis.

5. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1, characterized in that: In step 6, the relative thickness of the blade , which is the percentage of the thickness of the blade at a certain position relative to the chord length, where x is the distance from the leading edge to a specific position on the blade; t(x) is the thickness of the blade at position x; and C is the chord length of the blade.

6. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1, characterized in that: In step six, the extracted blade parameters include: blade angle at 0% of the blade hub, blade angle at 25% of the blade hub, blade angle at 50% of the blade hub, blade angle at 75% of the blade hub, blade angle at 100% of the blade hub, blade normal layer thickness at 0% of the blade hub, blade normal layer thickness at 25% of the blade hub, blade normal layer thickness at 50% of the blade hub, blade normal layer thickness at 75% of the blade hub, blade normal layer thickness at 100% of the blade hub, blade angle at 0% of the blade shroud, blade angle at 25% of the blade shroud, blade angle at 50% of the blade shroud, blade angle at 75% of the blade shroud, blade angle at 100% of the blade shroud, blade normal layer thickness at 0% of the blade shroud, blade normal layer thickness at 25% of the blade shroud, blade normal layer thickness at 50% of the blade shroud, blade normal layer thickness at 75% of the blade shroud, blade angle at 100%, blade normal layer thickness at 0% of the blade shroud, blade normal layer thickness at 25% of the blade shroud, blade normal layer thickness at 50% of the blade shroud, blade normal layer thickness at 75% of the blade shroud, and blade normal layer thickness at 100% of the blade shroud, 20 blade parameters.

7. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1 is characterized in that ,In step six, the sample output value solved refers to the fan static pressure efficiency and power.

8. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1 is characterized in that ,In step 6, the meta-model evaluation criteria are: prognostic coefficient To evaluate the quality of the established response surface model; is the sum of squared prediction errors, which are estimated based on cross-validation; is the total change, .

9. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1 is characterized in that ,In step seven, the objective function is to minimize the fan power and maximize the static pressure efficiency.

10. The method for optimizing the blade parameters of an axial flow fan of a charging pile based on a genetic algorithm according to claim 1, characterized in that: The charging pile axial flow fan is installed in the charging station.

Images