Low-resistance modeling design method for unmanned helicopter

Abstract

The invention belongs to the technical field of overall design of aircrafts, and particularly relates to a low-resistance modeling design method of an unmanned helicopter. Comprising the following steps: 1, selecting a control point set of longitudinal and transverse contours of an unmanned helicopter body, respectively establishing longitudinal and transverse contour parameterized control curves passing through the control points, and determining initial values of tension proportion parameters of the control points on the longitudinal and transverse curves; 2, constructing a corresponding parameterized control curve as an internal load space control optimization model, and solving the internal load space control optimization model by adopting a genetic algorithm on the basis of an optimization target with the minimum windward area and by taking the equipment and part loading space, the mounting gap and the process manufacturing as constraint conditions, so as to obtain a control curve of a typical section of a fuselage; and 3, importing the fuselage three-dimensional model into a fluid dynamic tool to calculate aerodynamic resistance, obtaining a fuselage sample aerodynamic data set, constructing an agent model for optimization, and obtaining an optimal unmanned helicopter model.

Description

Technical Field

[0001] This invention belongs to the field of aircraft overall design technology, and in particular relates to a low-drag styling design method for unmanned helicopters. Background Technology

[0002] The structural design of unmanned helicopters is the core foundation of their overall performance and mission effectiveness, directly affecting their flight efficiency, stability, payload capacity, and environmental adaptability. When designing the fuselage of an unmanned helicopter, it is necessary to consider not only having sufficient internal space for accommodating power transmission, fuel tanks, avionics, and other equipment / components, but also factors such as aerodynamic performance, weight control, and structural strength. This requires repeated coordination, comprehensive balancing, and iterative optimization across various disciplines to achieve the desired result.

[0003] Currently, the fuselage design of domestic unmanned helicopters is mainly based on reverse engineering or personal experience, which results in long design cycles, low efficiency, and the resulting fuselage designs generally have problems such as redundant internal space and high aerodynamic drag. Summary of the Invention

[0004] Purpose of the invention: To propose a low-drag styling design method for unmanned helicopters, which can optimize internal space, reduce fuselage aerodynamic drag, improve flight performance and mission efficiency, while reducing the number of design coordination and iterations, shortening the development cycle, and effectively improving the reliability and optimization efficiency of the styling scheme.

[0005] A low-drag design method for unmanned helicopters, the method comprising: Step 1: Select a set of control points for the longitudinal and transverse profiles of the unmanned helicopter fuselage, establish parametric control curves for the longitudinal and transverse profiles passing through these control points, and determine the initial values ​​of the tension proportional parameters for the control points on the longitudinal and transverse curves. ; Step 2: For the parametric control curves of the fuselage longitudinal and transverse profiles, select several typical cross sections and construct corresponding parametric control curves as internal load space control optimization models. Based on the optimization objective of minimizing the windward area, the loading space of equipment and components, installation gaps, and manufacturing processes are used as constraints. A genetic algorithm is used to solve the internal load space control optimization model to obtain the control curves of typical fuselage cross sections. Step 3: Change the tension ratio parameter of the control point on the longitudinal and transverse curves in Step 1 M times according to the preset rules. Repeat Step 2 each time to obtain M parameterized control curves based on the longitudinal and transverse contours of the fuselage and control curves of all typical profiles. Generate M three-dimensional fuselage models. Import the M three-dimensional fuselage models into the fluid dynamics tool to calculate aerodynamic drag and obtain the fuselage sample aerodynamic dataset. Construct a proxy model for optimization to obtain the optimal shape of the unmanned helicopter.

[0006] Furthermore, in step one, based on the loading space and installation gaps of the internal equipment and components, a set of control points for the longitudinal and transverse contours of the fuselage is selected, with the tension direction of the control point at the nose of the helicopter fuselage being the vertical direction.

[0007] Furthermore, the cross-sectional position and shape of the tail boom of the helicopter fuselage are determined; The parametric control curves of the fuselage's longitudinal and transverse profiles intersect with the cross-section at the tail boom, and the tension direction at the intersection point is tangent to the longitudinal and transverse control curves of the tail boom.

[0008] Furthermore, step 2 specifically includes: S21, constructing parametric control curves for typical fuselage cross-sectional profiles. (1) For the parameterized control curves of the fuselage longitudinal and transverse profiles, select the first... Four control points are obtained by intersecting a typical profile with the parametric control curves of the longitudinal and transverse profiles. Based on the layout of internal equipment and stealth requirements, corresponding control points are set between these four control points to form the first... A set of parameterized control points for a typical profile. ,in Indicates the first The three-dimensional coordinates of each control point in the fuselage coordinate system Number of control points; , This represents the total number of typical cross-sections. (2) Based on the first A set of parameterized control points for a typical cross-sectional profile, considering the longitudinal symmetry of the fuselage, is constructed. Parametric spline control curves:

[0009] in, , , , They represent , , Parametric control curves in three directions, , , , Hermite basis functions:

[0010] , , Control points , The derivative value of the parameter at:

[0011] Indicate control points and The distance between them , for , The tension ratio parameter, , The tangent directions of the corresponding control points are respectively , Unit vector: S22, with the minimum windward area of ​​the parametric spline control curve as the optimization objective, establish a target optimization mathematical model; The helicopter fuselage is symmetrically arranged, and the fuselage cross-section is... Since the value is constant, the mathematical model for the optimization objective is expressed as:

[0012] S23, considering the constraints of the loading space, installation clearance, and manufacturing process of the internal equipment and components, determine the constraints of the parametric spline control curve; (1) Constraint 1: The fuselage structure and internal equipment and components on any parametric spline control curve segment must not collide or interfere.

[0013] , This represents the coordinates of contour points on internal equipment and components within the parametric spline control curve. , The total number of contour points. This indicates the thickness of the fuselage structure and its clearance from internal equipment and components. (2) Constraint condition two: Any parametric spline control curve segment is smooth and free of bumps and valleys:

[0014] S24. A genetic algorithm is used to solve the inner load space control optimization model of the parameterized spline control curve. The inner load space control optimization model consists of the parameterized spline control curve and two constraints. S25, Increment the value by 1, and repeat S21~S24 to obtain K optimized internal space control optimization models.

[0015] Furthermore, S24 specifically refers to: (1) Population initialization, randomly generated All control point tension ratio parameter combinations By combining the coordinates of the control points and the tangent direction, the corresponding contour control curve is solved, thus forming... Chromosomes were used as the initial population; All control point tension ratio parameter combinations Tension ratio parameters for parameterized control points of all typical profile contours; (3) Fitness calculation: The internal load space control optimization model is transformed into a fitness function. For internal equipment and components that exceed the installation space constraints and manufacturing process constraints, a penalty term is introduced. The fitness function is then expressed as: ; (4) Genetic selection operation: calculate the fitness value of all chromosomes in the population, arrange them in descending order, retain the first 10% of chromosomes to enter the next generation population, without crossover and mutation operation, and use the roulette wheel method to perform crossover and mutation operation on the 90% of chromosomes that are the inferior population.

[0016] (5) Genetic crossover operation: Adaptive crossover operation is performed on the combination of tension ratio parameters of chromosomes of the inferior population according to the crossover probability; according to the combination of tension ratio parameters after crossover, the corresponding contour control curve is solved by combining the coordinates of the control point position and the tangent direction to form a new chromosome; calculate the fitness value of the new chromosome. If it is greater than the fitness value of the original chromosome, crossover repair is performed; otherwise, the original chromosome is retained. (6) Genetic mutation operation: Adaptive mutation operation is performed on the combination of tension ratio parameters of chromosomes of the inferior population according to the mutation probability. Based on the combination of tension ratio parameters after mutation, the corresponding contour control curve is solved by combining the coordinates of the control point position and the tangent direction to form a new chromosome and complete the mutation operation. (7) Termination condition judgment: Determine whether the maximum number of iterations has been reached. If so, output the optimal tension ratio parameter combination; otherwise, proceed to (4) for iterative optimization.

[0017] Furthermore, in step three, the preset rules are as follows: A series of control point tension ratio parameter sample points were obtained using the optimal Latin hypercube sampling method.

[0018] Furthermore, (1) for the M fuselage three-dimensional models, the fuselage sample aerodynamic datasets corresponding to the M fuselage three-dimensional models are obtained by fuselage three-dimensional modeling, structural mesh generation and CFD numerical simulation calculation; (2) Based on the aerodynamic dataset of the fuselage sample, a surrogate model is established with the minimum aerodynamic drag as the optimization objective:

[0019] (3) The genetic algorithm is used to optimize the fuselage aerodynamic surrogate model to obtain the optimal solution for the low-drag fuselage shape.

[0020] Furthermore, in (3), it is determined whether the aerodynamic drag optimization result satisfies the convergence criterion. If it does, the entire optimization process ends, and the current optimization result is the optimal unmanned helicopter shape; otherwise, the optimal Latin hypercube sampling method is used to obtain M. ‘ Sample points of tension proportional parameters at each control point, M ‘ >M.

[0021] In summary, the beneficial effects of the present invention are as follows: This invention proposes a low-drag styling design method for unmanned helicopters. It fully considers the control and optimization of internal space, effectively avoiding problems such as redundant internal space and excessive aerodynamic drag inherent in conventional styling designs. Furthermore, it employs a genetic algorithm to solve the optimization problem of the windward area of ​​typical fuselage cross-sections and the optimization problem of three-dimensional fuselage aerodynamic drag based on a surrogate model, enabling efficient acquisition of optimized fuselage styling solutions for unmanned helicopters. This method has been successfully applied to a certain type of unmanned helicopter and can be applied to other helicopters or fixed-wing aircraft in the future, demonstrating significant engineering application value. Attached Figure Description

[0022] Figure 1 This is a schematic flowchart of a low-drag styling design method for an unmanned helicopter provided in an embodiment of the present invention; Figure 2 These are schematic diagrams of various control curves and typical cross-sections provided in the embodiments of the present invention; Figure 3 This is a schematic diagram of the iterative fitness curve of a typical fuselage cross-sectional profile provided in an embodiment of the present invention; Figure 4 A schematic diagram of the optimized profile curve of a typical fuselage section provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the optimal fuselage design provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings.

[0024] This invention provides a low-drag styling design method for unmanned helicopters. It establishes parametric control curves for the longitudinal and lateral profiles of the fuselage, determining design variables and design space. For samples of the fuselage's longitudinal and lateral profile curves, parametric control curves of typical cross-sections are constructed as an internal load space control optimization model. Based on the optimization objective of minimizing the windward area, and considering constraints such as equipment / component loading space, maintenance clearances, and manufacturing processes, a genetic algorithm is used to solve the optimization model, obtaining the corresponding cross-sectional profile curves. The three-dimensional model generated from the fuselage's longitudinal, lateral, and typical cross-sectional profile curves is imported into a fluid dynamics (CFD) tool to calculate aerodynamic drag, thereby obtaining an aerodynamic dataset of fuselage samples. A surrogate model is then constructed for optimization to obtain the optimal unmanned helicopter styling scheme.

[0025] like Figure 1 As shown, a low-drag design method for an unmanned helicopter includes the following steps: Step 1: Select control point sets for the longitudinal and lateral profiles of the unmanned helicopter fuselage, establish parameterized control curves for the longitudinal and lateral profiles passing through these control points, and determine the tension ratio parameters of the control points on the curves. For design variables, such as Figure 2 As shown.

[0026] Select the control point set for the longitudinal and lateral profiles of the unmanned helicopter fuselage: Select the control point set for the longitudinal and lateral profiles of the fuselage based on the loading space and installation clearance of the internal equipment / components.

[0027] Step Two: For the longitudinal and transverse profile curve samples of the fuselage, select several typical cross-sections and construct corresponding parametric control curves as an internal load space control optimization model. Based on the optimization objective of minimizing the windward area, considering constraints such as equipment / component loading space, installation clearance, and manufacturing processes, a genetic algorithm is used to solve the optimization model to obtain the control curves of typical fuselage cross-sections, such as... Figure 2 As shown.

[0028] (1) Constructing parametric control curves for typical fuselage cross-sectional profiles 1) For the longitudinal and transverse contour curve samples of the fuselage, select the first one. Control points are obtained by intersecting a typical profile with the contour curve. Simultaneously, corresponding control points are set according to requirements such as the layout of internal equipment and stealth considerations, forming a control point set for the typical profile contour. ,in Indicates the first The three-dimensional coordinates of each control point in the fuselage coordinate system To control the number of points, , This represents the total number of typical cross-sections.

[0029] 2) Based on the contour control points and considering the longitudinal symmetry of the fuselage, the structure is... Parametric spline control curves: (1) In formula (1), ,in , , They represent , , Parametric control curves in three directions, , , , Hermite basis functions: (2) In formula (1) , Control points , The derivative value of the parameter at: (3) In formula (3), Indicate control points and The distance between them , for , The tension ratio parameter, , The tangent directions of the corresponding control points are respectively , Unit vector: (4) (2) Establish a mathematical model for target optimization with the goal of minimizing the windward area of ​​the profile curve. The fuselage cross-sectional area is a significant factor affecting the overall aerodynamic drag of the aircraft; therefore, minimizing the frontal area of ​​the cross-sectional profile curve is taken as the optimization objective. Considering the symmetrical arrangement of the unmanned helicopter fuselage and the fuselage cross-sectional area... Since the value is constant, the mathematical model for the optimization objective is expressed as: (5) (3) Taking into account constraints such as equipment / component loading space, installation clearance, and manufacturing process, determine the constraints of the contour curve. 1) There must be no collision or interference between the fuselage structure and internal equipment / components on any contour curve segment. (6) In formula (6), This indicates the coordinates of the outline points on the internally loaded equipment / components in the cross-section. , The total number of contour points. This indicates the thickness of the fuselage structure and the clearance between it and the internal equipment / components; in engineering, it is generally taken as 0.1m.

[0030] 2) Any contour curve segment is smooth and even, without any bumps or valleys. (7) (4) The genetic algorithm is used to solve the internal load space control optimization model of the typical fuselage cross section. 1) Optimize and identify the control point tension ratio parameter by identifying the fitness function and constraints of the problem model as spatial control optimization. 2) Population initialization. Randomly generated. All control point tension ratio parameter combination schemes By combining the coordinates of the control points and the tangent direction, the corresponding contour control curve is solved, thus forming... The chromosomes were used as the initial population.

[0031] 3) Fitness Calculation. The internal space control optimization function is transformed into a fitness function. For internal equipment / components that exceed installation space constraints and manufacturing process constraints, a penalty term is introduced. The fitness function can then be expressed as: (8) 4) Genetic selection operation. Calculate the fitness values ​​of all chromosomes in the population, arrange them in descending order, retain the top 10% of chromosomes to enter the next generation population without crossover or mutation operations, and use the roulette wheel method to perform crossover and mutation operations on the remaining 90% of chromosomes (called the inferior population).

[0032] 5) Genetic crossover operation. An adaptive crossover operation is performed on the tension ratio parameter combination of chromosomes in the inferior population based on the crossover probability. Specifically, for each chromosome in the inferior population, chromosomes to be crossed and crossover nodes are randomly generated. Genes at the crossover nodes of the two chromosomes to be crossed are exchanged, and duplicate genes at other nodes of the chromosomes are replaced with replacement genes. Based on the tension ratio parameter combination scheme after crossover, the corresponding contour control curve is solved using the coordinates of the control points and the tangent direction to form a new chromosome. The fitness value of the new chromosome is calculated. If the value is greater than the fitness value of the original chromosome, crossover repair is performed; otherwise, the original chromosome is retained.

[0033] 6) Genetic mutation operation. Adaptive mutation operation is performed on the combination of tension ratio parameters of chromosomes in the inferior population according to the mutation probability. That is, two different mutation nodes are randomly generated, and the genes of the chromosome to be mutated in the inferior population are interchanged at the two mutation nodes. According to the combination of tension ratio parameters after mutation, the corresponding contour control curve is solved by combining the coordinates of the control point position and the tangent direction to form a new chromosome and complete the mutation operation.

[0034] 7) Termination condition judgment: Determine whether the maximum number of iterations has been reached. If so, output the optimal tension ratio parameter combination scheme; otherwise, proceed to step 4) for iterative optimization.

[0035] (5) Increment the value by 1, repeat (1) to (4), and obtain K optimized internal space control optimization models.

[0036] (1) Use the optimal Latin hypercube sampling method to sample and obtain a series of control point tension ratio parameter sample points; repeat step two to obtain M control curves based on the longitudinal and transverse contour parameterization of the fuselage and all typical profiles, and generate M fuselage three-dimensional models; (2) For M fuselage three-dimensional models, the corresponding aerodynamic drag is obtained through fuselage three-dimensional modeling, structural mesh generation and CFD numerical simulation calculation, thereby obtaining the fuselage sample aerodynamic dataset; (3) Based on the aerodynamic dataset of the fuselage sample, a surrogate model is established with the minimum aerodynamic drag as the optimization objective: (9) (4) The genetic algorithm is used to optimize the fuselage aerodynamic surrogate model to obtain the optimal solution for the low-drag fuselage shape; Example illustration: The specific information regarding the fuselage design of a certain unmanned helicopter in this example is as follows: The unmanned helicopter has 5 control points for the longitudinal profile curve and 5 control points for the lateral profile curve. The corresponding control point coordinates and tangent vectors are shown in Table 1. Considering the symmetrical distribution of the lateral profile curve, 8 tension ratio parameters are formed as design variables, that is, the optimization problem in this embodiment is 8-dimensional; the range of design variables is (0,2], forming a design space.

[0037] Table 1. Control point information for the longitudinal and transverse profile curves of the fuselage

[0038] Three typical cross-sectional views of the fuselage of an unmanned helicopter are set, which are planes in the fuselage coordinate system. , , In addition to the control points obtained by intersecting with the longitudinal and transverse contour curves of the fuselage, these fuselage sections also have corresponding control points and constraints set according to the requirements of internal equipment layout and stealth. Considering the longitudinal symmetry of the fuselage, the control point information is shown in Table 2, and the contour constraint information of internal equipment / components of each fuselage section is shown in Table 3.

[0039] Table 2 Control point information for typical fuselage cross-sectional profile curves

[0040] Table 3. Constraint Information for Internal Equipment / Components in the Fuselage Section

[0041] The internal load space control optimization model of the typical fuselage cross-sectional contour curve proposed in this invention was solved using a genetic algorithm. The relevant parameters of the algorithm were set as follows: population size of 200, crossover probability of 0.5, mutation probability of 0.3, maximum number of iterations to terminate of 500; and penalty value of 0.5. This leads to the acquisition of an optimized scheme for the typical cross-sectional profile curve of the fuselage, such as... Figure 3 and Figure 4 As shown.

[0042] Within the design space based on the control points of the fuselage's longitudinal and transverse contour curves, the optimal Latin hypercube sampling method is used to optimize the variables. Fifty sample points were sampled; the aerodynamic drag calculation parameters for the 3D fuselage model were set to an air density of 1.225 kg / m³ and a relative speed of 60 m / s; a Kriging surrogate model was constructed for optimization to obtain the optimal fuselage shape for the unmanned helicopter. (See...) Figure 5 .

[0043] Table 4. Tension information of the optimal fuselage profile curve.

[0044] The proposed method for low-drag styling design of unmanned helicopters based on genetic algorithms fully considers the control and optimization of internal space within the fuselage, and can efficiently obtain optimized low-drag styling solutions.

[0045] Key points of this invention: The key point of this invention is the low-drag styling design method for unmanned helicopter fuselages based on genetic algorithms. It is applicable to low-drag aerodynamic shape design with constraints on internal space and personalized shapes, and can efficiently obtain optimized low-drag styling solutions for fuselages.

[0046] The low-drag styling optimization design variables can be the design variables of the fuselage longitudinal and transverse profile curves, or the design variables of typical cross-sectional profile curves can be added on this basis to form a higher-dimensional design space, which can participate in the surrogate model optimization to obtain the optimal solution of low-drag styling.

[0047] The surrogate model can be Kriging (Gaussian process regression), multinomial regression, artificial neural networks, or other surrogate models.

[0048] The genetic operations described can be performed by first crossing over and then mutation, or by first mutation and then crossing over.

[0049] This invention proposes a low-drag styling design method for unmanned helicopters. It fully considers the control and optimization of internal space, effectively avoiding problems such as redundant internal space and excessive aerodynamic drag inherent in conventional styling designs. Furthermore, it employs a genetic algorithm to solve the optimization problem of the windward area of ​​typical fuselage cross-sections and the optimization problem of three-dimensional fuselage aerodynamic drag based on a surrogate model, enabling efficient acquisition of optimized fuselage styling solutions for unmanned helicopters. This method has been successfully applied to a certain type of unmanned helicopter and can be applied to other helicopters or fixed-wing aircraft in the future, demonstrating significant engineering application value.

Claims

1. A low-drag design method for an unmanned helicopter, characterized in that, The method includes: Step 1: Select a set of control points for the longitudinal and transverse profiles of the unmanned helicopter fuselage, establish parametric control curves for the longitudinal and transverse profiles passing through these control points, and determine the initial values ​​of the tension proportional parameters for the control points on the longitudinal and transverse curves. ; Step 2: For the parametric control curves of the fuselage longitudinal and transverse profiles, select several typical cross sections and construct corresponding parametric control curves as internal load space control optimization models. Based on the optimization objective of minimizing the windward area, the loading space of equipment and components, installation gaps, and manufacturing processes are used as constraints. A genetic algorithm is used to solve the internal load space control optimization model to obtain the control curves of typical fuselage cross sections. Step 3: Change the tension ratio parameter of the control point on the longitudinal and transverse curves in Step 1 M times according to the preset rules. Repeat Step 2 each time to obtain M parameterized control curves based on the longitudinal and transverse contours of the fuselage and control curves of all typical profiles. Generate M three-dimensional fuselage models. Import the M three-dimensional fuselage models into the fluid dynamics tool to calculate aerodynamic drag and obtain the fuselage sample aerodynamic dataset. Construct a proxy model for optimization to obtain the optimal shape of the unmanned helicopter.

2. The low-drag styling design method for an unmanned helicopter according to claim 1, characterized in that, In step one, based on the loading space and installation gaps of the internal equipment and components, a set of control points for the longitudinal and transverse contours of the fuselage is selected, with the tension direction of the control point at the nose of the helicopter fuselage being the vertical direction.

3. The low-drag styling design method for an unmanned helicopter according to claim 2, characterized in that, The cross-sectional position and shape of the tail boom of the helicopter fuselage are fixed; The parametric control curves of the fuselage's longitudinal and transverse profiles intersect with the cross-section at the tail boom, and the tension direction at the intersection point is tangent to the longitudinal and transverse control curves of the tail boom.

4. The low-drag styling design method for an unmanned helicopter according to claim 2, characterized in that, Step 2 specifically includes: S21, constructing parametric control curves for typical fuselage cross-sectional profiles. (1) For the parameterized control curves of the fuselage longitudinal and transverse profiles, select the first... Four control points are obtained by intersecting a typical profile with the parametric control curves of the longitudinal and transverse profiles. Based on the layout of internal equipment and stealth requirements, corresponding control points are set between these four control points to form the first... A set of parameterized control points for a typical profile. ,in Indicates the first The three-dimensional coordinates of each control point in the fuselage coordinate system Number of control points; , This represents the total number of typical cross-sections. (2) Based on the first A set of parameterized control points for a typical cross-sectional profile, considering the longitudinal symmetry of the fuselage, is constructed. Parametric spline control curves: in, , , , They represent , , Parametric control curves in three directions, , , , Hermite basis functions: , , Control points , The derivative value of the parameter at: Indicate control points and The distance between them , for , The tension ratio parameter, , The tangent directions of the corresponding control points are respectively , Unit vector: S22, with the minimum windward area of ​​the parametric spline control curve as the optimization objective, establish a target optimization mathematical model; The helicopter fuselage is symmetrically arranged, and the fuselage cross-section is... Since the value is constant, the mathematical model for the optimization objective is expressed as: S23, considering the constraints of the loading space, installation clearance, and manufacturing process of the internal equipment and components, determine the constraints of the parametric spline control curve; (1) Constraint 1: The fuselage structure and internal equipment and components on any parametric spline control curve segment must not collide or interfere. , This represents the coordinates of contour points on internal equipment and components within the parametric spline control curve. , The total number of contour points. This indicates the thickness of the fuselage structure and its clearance from internal equipment and components. (2) Constraint condition two: Any parametric spline control curve segment is smooth and free of bumps and valleys: S24. A genetic algorithm is used to solve the inner load space control optimization model of the parameterized spline control curve. The inner load space control optimization model consists of the parameterized spline control curve and two constraints. S25, Increment the value by 1, and repeat S21~S24 to obtain K optimized internal space control optimization models.

5. The low-drag styling design method for an unmanned helicopter according to claim 2, characterized in that, S24 specifically refers to: (1) Population initialization, randomly generated All control point tension ratio parameter combinations By combining the coordinates of the control points and the tangent direction, the corresponding contour control curve is solved, thus forming... Chromosomes were used as the initial population; All control point tension ratio parameter combinations Tension ratio parameters for parameterized control points of all typical profile contours; (3) Fitness calculation: The internal load space control optimization model is transformed into a fitness function. For internal equipment and components that exceed the installation space constraints and manufacturing process constraints, a penalty term is introduced. The fitness function is then expressed as: ; (4) Genetic selection operation: calculate the fitness value of all chromosomes in the population, arrange them in descending order, retain the first 10% of chromosomes to enter the next generation population, without crossover and mutation operation, and use the roulette wheel method to perform crossover and mutation operation on the 90% of chromosomes that are the inferior population. (5) Genetic crossover operation: Adaptive crossover operation is performed on the combination of tension ratio parameters of chromosomes of the inferior population according to the crossover probability; according to the combination of tension ratio parameters after crossover, the corresponding contour control curve is solved by combining the coordinates of the control point position and the tangent direction to form a new chromosome; calculate the fitness value of the new chromosome. If it is greater than the fitness value of the original chromosome, crossover repair is performed; otherwise, the original chromosome is retained. (6) Genetic mutation operation: Adaptive mutation operation is performed on the combination of tension ratio parameters of chromosomes of the inferior population according to the mutation probability. Based on the combination of tension ratio parameters after mutation, the corresponding contour control curve is solved by combining the coordinates of the control point position and the tangent direction to form a new chromosome and complete the mutation operation. (7) Termination condition judgment: Determine whether the maximum number of iterations has been reached. If so, output the optimal tension ratio parameter combination; otherwise, proceed to (4) for iterative optimization.

6. The low-drag styling design method for an unmanned helicopter according to claim 5, characterized in that, In step three, the preset rules are as follows: A series of control point tension ratio parameter sample points were obtained using the optimal Latin hypercube sampling method.

7. The low-drag styling design method for an unmanned helicopter according to claim 5, characterized in that, (1) For M fuselage 3D models, the fuselage sample aerodynamic datasets corresponding to the M fuselage 3D models are obtained by fuselage 3D modeling, structural mesh generation and CFD numerical simulation calculation; (2) Based on the aerodynamic dataset of the fuselage sample, a surrogate model is established with the minimum aerodynamic drag as the optimization objective: (3) The genetic algorithm is used to optimize the fuselage aerodynamic surrogate model to obtain the optimal solution for the low-drag fuselage shape.

8. The low-drag styling design method for an unmanned helicopter according to claim 7, characterized in that, In (3), it is determined whether the aerodynamic drag optimization result meets the convergence criterion. If it does, the entire optimization process ends, and the current optimization result is the optimal unmanned helicopter shape; otherwise, the optimal Latin hypercube sampling method is used to obtain M. ‘ Sample points of tension proportional parameters at each control point, M ‘ >M.

9. A low-drag structure for an unmanned helicopter, characterized in that, It is designed using the design method described in any one of claims 1-8.

Images