Fan blade design method and device and electronic equipment

Abstract

The invention provides a fan blade design method and device and electronic equipment. The method comprises the steps that initial parameters are obtained, a fan blade model is constructed according to the initial parameters, the initial parameters are parameters representing the initial structure of a fan blade, and the fan blade model is a physical model of the fan blade; target performance parameters of the fan blade model are obtained, a multi-target optimization function is constructed according to the target performance parameters, and the target performance parameters are parameters representing fan performance; and solving a Pareto solution of the multi-objective optimization function through a multi-objective genetic algorithm to obtain a target parameter value of the fan blade model, and designing the fan blade according to the target parameter value. By means of the method and device, the problem that in the prior art, design of fan blades of an air conditioner mainly depends on experience of designers, and consequently the optimization efficiency of the blade structure is low is solved.

Description

Technical Field

[0001] This application relates to the field of air conditioning design technology, and more specifically, to a design method, apparatus, computer-readable storage medium, and electronic device for fan blades. Background Technology

[0002] In the field of ventilation and air conditioning, axial fan blades, as core components of ventilation equipment and air conditioning systems, directly determine the system's aerodynamic efficiency, noise level, and overall operational stability. With modern industry's increasing demands for high efficiency, low noise, and high reliability, the design optimization of axial fan blades has become a crucial step in improving system performance. However, current axial fan blade design methods primarily rely on designers' experience and traditional trial-and-error approaches, resulting in the following main problems: First, the design process is highly dependent on designers' experience and subjective judgment; second, traditional design methods require designers to frequently manually modify and adjust the fan blade model, leading to low optimization efficiency and difficulty in meeting design requirements under complex operating conditions. Summary of the Invention

[0003] The main objective of this application is to provide a design method, apparatus, computer-readable storage medium, and electronic device for wind turbine blades, so as to at least solve the problem that the design of air conditioning wind turbine blades mainly relies on the experience of designers, resulting in low efficiency in blade structure optimization.

[0004] To achieve the above objectives, according to one aspect of this application, a method for designing wind turbine blades is provided, comprising: obtaining initial parameters; constructing a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade; obtaining target performance parameters of the wind turbine blade model, and constructing a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the performance of the wind turbine; solving the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and designing the wind turbine blade based on the target parameter values.

[0005] Optionally, obtaining initial parameters and constructing a wind turbine blade model based on the initial parameters includes: obtaining the angle parameters and size parameters of the wind turbine blade to obtain the initial parameters, wherein the angle parameters are parameters representing the installation angle of the blade, and the size parameters are parameters representing the size of the blade; and constructing a three-dimensional model based on the initial parameters to obtain the wind turbine blade model.

[0006] Optionally, the target performance parameters of the wind turbine blade model are obtained, and a multi-objective optimization function is constructed based on the target performance parameters, including: obtaining the air volume parameter, power parameter, and noise parameter of the wind turbine blade model to obtain the target performance parameters, wherein the air volume parameter represents the air volume generated by the wind turbine blade model, the power parameter represents the power of the wind turbine blade model, and the noise parameter represents the noise of the wind turbine blade model; and constructing the multi-objective optimization function with the objectives of maximizing the air volume parameter, minimizing the power parameter, and minimizing the noise parameter.

[0007] Optionally, the target parameter values ​​of the wind turbine blade model are obtained by solving the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm, including: using the initial parameters as the initial population parameters of the multi-objective genetic algorithm, wherein the initial population parameters represent a set of initial values ​​of the multi-objective genetic algorithm; an iterative step, obtaining the iteration step size and iteration number of the multi-objective genetic algorithm, performing iterative calculation on the initial population parameters according to the iteration step size and iteration number to obtain new population parameters, wherein the new population parameters represent a set of new structural parameters obtained by iterative calculation of the initial parameters of the wind turbine blade; calculating the multi-objective optimization function value corresponding to each new population parameter until the multi-objective optimization function value satisfies the iteration exit condition of the multi-objective genetic algorithm, exiting the multi-objective genetic algorithm, and determining the target parameter value as the multi-objective optimization function value, wherein the iteration exit condition includes at least the current iteration number being greater than or equal to the iteration number.

[0008] Optionally, calculating the multi-objective optimization function value corresponding to each of the new population parameters includes: dividing the wind turbine blade model into a mesh to obtain a meshed wind turbine blade model; and using fluid dynamics software to calculate the multi-objective optimization function value corresponding to the new population parameter of the meshed wind turbine blade model.

[0009] Optionally, the initial population parameters are iteratively calculated according to the iteration step size and the number of iterations to obtain new population parameters, including: adjusting the parameters of the initial population according to the iteration step size to obtain a offspring population; merging the offspring population with the initial population to obtain a merged population; and filtering the parameters in the merged population to obtain the new population parameters.

[0010] Optionally, the parameters in the merged population are filtered to obtain the new population parameters, including: calculating the crowding degree of the parameters in the merged population, wherein the crowding degree represents the distance between two parameters; and determining the parameter as the new population parameter if the crowding degree is greater than a preset threshold.

[0011] According to another aspect of this application, a wind turbine blade design apparatus is provided, comprising: a first construction unit, configured to acquire initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade; a second construction unit, configured to acquire target performance parameters of the wind turbine blade model and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the performance of the wind turbine; and a design unit, configured to solve the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0012] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the aforementioned wind turbine blade design methods.

[0013] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for performing any of the wind turbine blade design methods described above.

[0014] By applying the technical solution of this application, initial parameters are obtained, a fan blade model is constructed based on the initial parameters, target performance parameters of the fan blade model are obtained, and a multi-objective optimization function is constructed based on the target performance parameters, whereby the target performance parameters represent the fan performance. The multi-objective optimization function is solved using a multi-objective genetic algorithm to obtain the target parameter values ​​of the fan blade model, and the fan blades are designed based on these target parameter values. Compared with existing technologies where the design of air conditioning fan blades mainly relies on the designer's experience, this application automatically obtains the target parameter values ​​of the fan blade model by establishing a fan blade model and a multi-objective optimization function, and solving the multi-objective optimization function using a multi-objective genetic algorithm. Therefore, it can solve the problem of low optimization efficiency of fan blade structure caused by reliance on manual experience in the design of fan blades in existing technologies, and improve the optimization efficiency of blade structure. Attached Figure Description

[0015] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0016] Figure 1A schematic flowchart of a wind turbine blade design method according to an embodiment of this application is shown;

[0017] Figure 2 A flowchart illustrating a specific multi-objective optimization method for wind turbine blades according to an embodiment of this application is shown.

[0018] Figure 3 A flowchart of a specific multi-objective genetic algorithm for a wind turbine blade, according to an embodiment of this application, is shown.

[0019] Figure 4 A schematic diagram of an initial axial flow fan blade model provided according to an embodiment of this application is shown;

[0020] Figure 5 A comparison diagram of the original and optimized wind turbine blade performance provided according to an embodiment of this application is shown;

[0021] Figure 6 A schematic diagram of an optimized wind turbine blade model provided according to an embodiment of this application is shown;

[0022] Figure 7 A structural block diagram of a wind turbine blade design device provided according to an embodiment of this application is shown. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0027] Axial flow fan blades: A type of fan blade in which the airflow direction is in the same direction as the axis of the fan blade.

[0028] As described in the background section, the design of air conditioner fan blades in the prior art mainly relies on the experience of designers, resulting in low efficiency in optimizing the blade structure. In order to solve the problem that the design of air conditioner fan blades mainly relies on the experience of designers, resulting in low efficiency in optimizing the blade structure, the embodiments of this application provide a fan blade design method, apparatus, computer-readable storage medium and electronic device.

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] This embodiment provides a method for designing wind turbine blades that run on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 1 This is a flowchart of a wind turbine blade design method according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0032] Step S201: Obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade.

[0033] Specifically, initial parameters form the basis of the wind turbine blade geometry, including but not limited to the blade installation angle, leading and trailing edge angle, chord length, bend angle, sweep height, and installation angle. These initial parameters are used to model the wind turbine blades. By setting parameters such as chord length and bend angle, different blade shapes can be generated.

[0034] Step S202: Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance;

[0035] Specifically, after establishing the physical model of the wind turbine blades, the next step is to determine and measure the model's performance parameters. These parameters reflect the operating characteristics of the wind turbine blades, such as aerodynamic performance (e.g., efficiency, flow rate) and noise levels. The target performance parameters mainly focus on two key points: the performance of the wind turbine blades (e.g., efficiency, flow rate) and the noise generated by the wind turbine blades. Based on these target performance parameters, a multi-objective optimization function is constructed. This multi-objective optimization function is a mathematical expression that the optimization algorithm attempts to maximize or minimize, reflecting the goals the designer wants to achieve through optimization. The multi-objective optimization function aims to optimize the performance of the wind turbine blades while considering noise control.

[0036] Step S203: Solve the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0037] Specifically, a multi-objective genetic algorithm is a heuristic optimization method used to handle problems with multiple competing or complementary optimization objectives. In this embodiment, the multi-objective optimization function includes multiple objectives such as the aerodynamic performance and noise control of the wind turbine blades. The multi-objective genetic algorithm searches for and identifies solutions that achieve a good balance across multiple objectives by simulating natural selection and genetic processes, such as selection, crossover, and mutation. The target parameter values ​​of the wind turbine blade model are selected based on actual needs. The NSGA-II (Non-dominated Sorting Genetic Algorithm II) algorithm is used as the specific implementation of the multi-objective genetic algorithm. This algorithm maintains the diversity of the population through non-dominated sorting and crowding calculation, and iterates step by step. Each generation of the population (i.e., the wind turbine blade design) is selected and evolved based on its performance in the multi-objective optimization function space, thereby approximating the Pareto optimal solution set and obtaining the target parameter values ​​of the wind turbine blade model.

[0038] This embodiment obtains initial parameters, constructs a fan blade model based on these parameters, acquires the target performance parameters of the fan blade model, and constructs a multi-objective optimization function based on these parameters. The target performance parameters represent the fan's performance. A multi-objective genetic algorithm is used to solve the multi-objective optimization function to obtain the target parameter values ​​of the fan blade model. The fan blades are then designed based on these target parameter values. Compared to existing technologies where the design of air conditioning fan blades relies heavily on the designer's experience, this application automatically obtains the target parameter values ​​of the fan blade model by establishing a fan blade model and a multi-objective optimization function, and then solving the multi-objective optimization function using a multi-objective genetic algorithm. Therefore, it solves the problem of low optimization efficiency caused by the reliance on manual experience in fan blade design in existing technologies, and improves the optimization efficiency of the blade structure.

[0039] In the specific implementation process, the above step S201, obtaining initial parameters and constructing a wind turbine blade model based on the initial parameters, can be achieved through the following steps: Step S2011: Obtain the angle parameters and dimension parameters of the wind turbine blade to obtain the initial parameters, wherein the angle parameters represent the installation angle of the blade, and the dimension parameters represent the size of the blade; Step S2012: Construct a three-dimensional model based on the initial parameters to obtain the wind turbine blade model. This method constructs a wind turbine blade model through the above steps, which facilitates the simulation of the structure of a real wind turbine blade and the corresponding performance, and facilitates the determination of optimal structural parameters.

[0040] Specifically, in designing axial flow fan blades, the first step is to collect and determine some basic design parameters, mainly including angle parameters and dimensional parameters. Angle parameters focus on the blade's installation angle, which determines the relative relationship between the blade and the airflow direction, directly affecting airflow guidance and blade efficiency. Dimensional parameters involve the overall size and specific geometry of the blade, such as its thickness, length, and curvature. These dimensional parameters collectively shape the blade's shape, thus affecting its mechanical performance and hydrodynamic behavior. Based on these initial parameters, a three-dimensional model is constructed to obtain the fan blade model. Having the angle and dimensional parameters, these abstract values ​​are then converted into a concrete three-dimensional model. The three-dimensional model not only visually represents the blade's appearance and structure but also serves as the foundation for further research and analysis. For example, using professional computer-aided design (CAD) software, the angle and dimensional parameters are used as input, and the software's modeling tools and parametric design functions generate a three-dimensional geometric model of the fan blade for subsequent hydrodynamic analysis and performance evaluation.

[0041] In some optional implementations, step S202, obtaining the target performance parameters of the wind turbine blade model and constructing a multi-objective optimization function based on the target performance parameters, can be achieved through the following steps: Step S2021: Obtain the airflow parameters, power parameters, and noise parameters of the wind turbine blade model to obtain the target performance parameters, wherein the airflow parameter represents the airflow generated by the wind turbine blade model, the power parameter represents the power of the wind turbine blade model, and the noise parameter represents the noise of the wind turbine blade model; Step S2022: Construct the multi-objective optimization function with the objectives of maximizing the airflow parameter, minimizing the power parameter, and minimizing the noise parameter. This method, through the above steps, seeks blade designs that exhibit excellent performance in aerodynamics, energy consumption, and acoustics, thereby meeting the comprehensive requirements of modern industry for high performance, low energy consumption, and low noise in wind turbine blades.

[0042] Specifically, a crucial step in designing axial fan blades is evaluating their performance under actual operating conditions. This includes obtaining airflow parameters (the amount of airflow generated by the blades), power parameters (the energy consumed during blade operation), and noise parameters (the acoustic effects produced during blade operation). These parameters collectively constitute the target performance parameters, which are key indicators for evaluating the quality of the blade design. These parameters are typically obtained through experimental testing or numerical simulation, such as computational fluid dynamics (CFD) analysis. The multi-objective optimization function is set to simultaneously maximize airflow parameters, minimize power parameters, and minimize noise parameters. That is, the goal of design optimization is to ensure high airflow output while minimizing required power and operating noise, achieving a highly efficient, energy-saving, and low-noise fan blade design. Then, optimization algorithms, such as the aforementioned NSGA-II, are used to search for and identify design schemes that achieve the optimal balance among the three objectives of airflow, power, and noise.

[0043] In some alternative implementations, step S203, by solving the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, can be achieved through the following steps: Step S2031: Using the initial parameters as the initial population parameters of the multi-objective genetic algorithm, wherein the initial population parameters represent a set of initial values ​​for the multi-objective genetic algorithm; Step S2032: An iterative step, obtaining the iteration step size and iteration number of the multi-objective genetic algorithm, and iteratively calculating the initial population parameters according to the iteration step size and iteration number to obtain new population parameters, wherein the new population parameters represent a set of new structural parameters obtained by iterative calculation of the initial parameters of the wind turbine blade; Step S2033: Calculating the multi-objective optimization function value corresponding to each new population parameter until the multi-objective optimization function value satisfies the iteration exit condition of the multi-objective genetic algorithm, exiting the multi-objective genetic algorithm, and determining the target parameter value as the multi-objective optimization function value, wherein the iteration exit condition includes at least the current iteration number being greater than or equal to the iteration number. This method obtains the target parameter values ​​of the optimal wind turbine blade model through the above steps. This allows for finding a balance point among multiple target performance parameters and automatically solving for the optimal solution, making blade structure optimization more efficient.

[0044] Specifically, the initial design parameters of the wind turbine blade angle and size are used as the initial state of the genetic algorithm population, and iterative improvement is achieved through the algorithm's genetic mechanism. The iteration step size and number of iterations are crucial parameters in MOGA (Multi-Objective Genetic Algorithm), controlling the search range and depth. The iteration step size determines the magnitude of parameter changes in each generation, while the number of iterations limits the total cycle of the algorithm. In each iteration, the algorithm performs selection, crossover, and mutation operations to generate a new population. Selection is based on the fitness of individuals in the current population, i.e., their performance on the multi-objective optimization function; crossover and mutation operations are used to generate new combinations of design parameters to achieve better performance. Iterative computation creates a new population by updating parameter values, with each individual representing a set of possible wind turbine blade design parameters. These parameters, through iterative processing by the algorithm, gradually approach design points that perform well across multiple objectives such as airflow, power, and noise. For each individual in the new population, its corresponding airflow, power, and noise parameters are calculated using numerical simulation methods such as CFD, thus determining its position in the multi-objective optimization function space. An iteration exit condition is the criterion for terminating the algorithm's execution. This includes at least one condition: the current iteration count must be greater than or equal to a preset iteration count. This means that when the algorithm reaches the preset iteration count, the iteration process will stop regardless of whether an absolutely optimal solution has been found. Setting an iteration exit condition is to prevent the algorithm from getting stuck in an endless loop, and it also serves as effective management of computational resources and time. Generally, when the maximum number of iterations is reached, the individuals in the population are close enough to the optimization objective that an optimal or satisfactory solution can be selected.

[0045] In some optional implementations, step S2033 can be achieved through the following steps: meshing the wind turbine blade model to obtain a meshed wind turbine blade model; and using fluid dynamics software to calculate the multi-objective optimization function values ​​corresponding to the new population parameters of the meshed wind turbine blade model. This method, through the above steps and with the aid of fluid dynamics software, can efficiently calculate the performance indicators of the blade design in terms of airflow, power, and noise, thereby facilitating the selection of a design scheme with superior performance.

[0046] Specifically, before performing any type of fluid dynamics analysis, the three-dimensional model of the wind turbine blade needs to be divided into a large number of small units, i.e., a mesh. Meshing is used to discretize the continuous fluid domain, allowing fluid dynamics equations to be applied to each mesh unit, thereby solving complex fluid dynamics problems numerically. Specialized fluid dynamics software (such as ANSYS Fluent, CFX, StarCCM+, etc.) is used to simulate the blade's performance under aerodynamic forces, including calculating performance indicators such as airflow, required power, and noise generated by the blade. In the software, the meshed wind turbine blade model is first imported, and then boundary conditions, fluid properties, and solution parameters are set. The software will solve the fluid dynamics equations based on the established physical model and numerical methods to obtain the performance data of the blade design. This data is then used to calculate the multi-objective optimization function values ​​corresponding to the new population parameters, i.e., the quantitative expression of optimization objectives such as airflow, power, and noise, providing necessary feedback for the multi-objective genetic algorithm.

[0047] In some optional implementations, step S2032 can be achieved through the following steps: Step S2034: Adjust the parameters of the initial population according to the iteration step size to obtain a offspring population; Step S2035: Merge the offspring population with the initial population to obtain a merged population; Step S2036: Filter the parameters in the merged population to obtain the parameters of the new population. This method performs iterative calculations through the above steps. Through multiple iterations, the algorithm can explore the design space and identify design schemes that demonstrate balanced or superior performance across multiple objectives such as airflow, power, and noise, thereby significantly improving the performance and efficiency of wind turbine blade design.

[0048] Specifically, the iteration step size determines the magnitude of population parameter changes in the genetic algorithm. During optimization, the algorithm fine-tunes the parameters in the initial population according to the iteration step size, generating new parameter combinations through genetic operations such as crossover and mutation, thus producing the offspring population. After generating the offspring population, the algorithm merges these newly generated individuals with the current initial population to form a larger merged population. The merged population includes the current best individual and newly explored individuals, providing a wider range of design samples for subsequent selection, crossover, and mutation. Selection is a crucial step in the genetic algorithm. Based on the individual's performance on the multi-objective optimization function, it retains those with better performance through a selection mechanism while eliminating those with poor performance. The selection process ensures that the population evolves towards the optimization objective. The selection process typically includes steps such as non-dominated sorting and calculating crowding distance. Non-dominated sorting is used to identify individuals that are not dominated by other individuals on any objective, i.e., Pareto optimal individuals; crowding distance calculation is used to maintain the diversity of individuals on the Pareto front. Based on these evaluations, the algorithm selects a certain number of individuals to form a new population, which will be used for the next round of iterative computation.

[0049] In some optional implementations, step S2036 can be achieved by the following steps: calculating the crowding degree of a parameter in the merged population, wherein the crowding degree represents the distance between two parameters; and determining the parameter as the new population parameter if the crowding degree is greater than a preset threshold. This method, by calculating the crowding degree of individuals in the merged population and determining individuals with crowding degrees higher than a preset threshold as new population parameters, can preserve population diversity and avoid premature convergence.

[0050] Specifically, crowding is an indicator used in multi-objective optimization to measure the density of an individual's distribution within the multi-objective optimization function space. It reflects the distance between individuals across multi-objective optimization function values, i.e., the differences in multi-objective performance such as airflow, power, and noise resulting from different combinations of design parameters. Crowding is typically calculated based on an individual's ranking position in each multi-objective optimization function and the differences in multi-objective optimization function values ​​between individuals. For each multi-objective optimization function, the algorithm calculates the neighbor differences between individuals and then sums them across all multi-objective optimization functions to obtain the total crowding of the individuals. In merging populations, individuals with higher crowding—that is, those farther from their neighbors in the multi-objective optimization function space—are more likely to be selected as members of the new population. A preset threshold is a criterion used to select individuals, helping the algorithm identify design parameter combinations with unique performance advantages while maintaining population diversity.

[0051] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the wind turbine blade design method of this application will be described in detail below with reference to specific embodiments.

[0052] This embodiment relates to a flowchart of a specific multi-objective optimization method for wind turbine blades, as shown below. Figure 2 As shown, it includes the following steps:

[0053] Step S1: Begin;

[0054] Step S2: Parametric model (wind turbine blade model);

[0055] Step S3: Mesh generation and processing;

[0056] Step S4: Simulation calculation and result output;

[0057] Step S5: Result extraction and optimization;

[0058] Step S6: Is the iteration termination condition met? If yes, proceed to step S7; otherwise, return to step S2.

[0059] Step S7: Output the Pareto solution.

[0060] This embodiment relates to a flowchart of a specific multi-objective genetic algorithm for wind turbine blades, as shown below. Figure 3 As shown, it includes the following steps:

[0061] Step S8: Begin;

[0062] Step S9: Initialize the population;

[0063] Step S10: Determine whether it is a first-generation subgroup. If yes, proceed to step S11; otherwise, proceed to step S17.

[0064] Step S11: The parent and offspring generations are merged to form a new population;

[0065] Step S12: Non-dominated sorting;

[0066] Step S13: Crowding degree calculation;

[0067] Step S14: Selection, crossover, mutation;

[0068] Step S15: Select individuals to form offspring;

[0069] Step S16: Is the iteration termination condition met? If yes, output the result; otherwise, proceed to step S11.

[0070] Step S17: Individual fitness calculation;

[0071] Step S18: Non-dominated sort;

[0072] Step S19: Select, crossover, mutate, and return to step S10.

[0073] Taking a 3-bladed axial flow fan with a diameter of 550mm as an example, using CFX as the simulation software, such as Figure 4 The diagram shows the initial axial flow fan blade model. Without changing the hub and rim diameters and maintaining the rated speed, the fan blade is optimized. Typically, a three-dimensional axial flow fan blade can be considered as a stack of multiple two-dimensional blade profiles. The stacking characteristics are described by the bend angle and sweep height. Each two-dimensional blade profile can be described by features such as the leading edge direction angle, trailing edge direction angle, chord length, and installation angle. These parameter values ​​are used as the initial parameters for the fan blade model, as shown in Table 1.

[0074] Table 1

[0075]

[0076] After meshing the aforementioned wind turbine blade model, simulation calculations were performed. The ratio of the simulated flow rate to the axial torque was used as the performance evaluation index of the wind turbine blade. Research shows that aerodynamic noise mainly originates from the stretching and rupture of vortices in the flow field. The main aerodynamic noise sources of low-speed axial flow fans are blade trailing edge vortex shedding noise and blade tip vortex noise, with the former being significantly stronger than the latter. Therefore, the noise evaluation index is expressed by the vorticity of the blade trailing edge. The above evaluation function was calculated using simulation software, and a repeatedly executable script file was written to automatically mesh and output the results. The value ranges of these structural parameters are shown in Table 2.

[0077] Table 2

[0078]

[0079]

[0080] Using the aforementioned optimization design method and the developed automated design platform, the population size was set to 60, and the iterations were performed for 10 generations. The calculation results were exported, and the model with a noise evaluation similar to the original wind turbine blade but a higher performance evaluation was selected and named Wind Turbine Blade No. 1. The performance comparison between the original wind turbine blade and the optimized wind turbine blade is shown in the figure below. Figure 5 As shown, the optimized wind turbine blade model is as follows: Figure 6 As shown, the values ​​are shown in Table 3:

[0081] Table 3

[0082]

[0083] After adding ribs to the hub of the No. 1 wind turbine model and the original wind turbine model to meet the testing requirements, 3D prototypes were made and tested and compared on a dual-blade outdoor unit. The target performance parameters of the original wind turbine and the No. 1 wind turbine are shown in Tables 4 and 5, respectively.

[0084] Table 4

[0085]

[0086]

[0087] Table 5

[0088]

[0089] In the experimental test, the original blade model and the No. 1 blade model had an air volume advantage of about 4% at the same power, and the noise value was not much different at the same speed, proving the feasibility of the multi-objective optimization design method.

[0090] This application also provides a wind turbine blade design apparatus. It should be noted that the wind turbine blade design apparatus of this application can be used to execute the wind turbine blade design method provided in this application. This apparatus is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0091] The following describes the design device for wind turbine blades provided in the embodiments of this application.

[0092] Figure 7 This is a schematic diagram of a wind turbine blade design device according to an embodiment of this application. Figure 7 As shown, the device includes:

[0093] The first construction unit 10 is used to obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade.

[0094] Specifically, initial parameters form the basis of the wind turbine blade geometry, including but not limited to the blade installation angle, leading and trailing edge angle, chord length, bend angle, sweep height, and installation angle. These initial parameters are used to model the wind turbine blades. By setting parameters such as chord length and bend angle, different blade shapes can be generated.

[0095] The second construction unit 20 is used to obtain the target performance parameters of the wind turbine blade model and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance;

[0096] Specifically, after establishing the physical model of the wind turbine blades, the next step is to determine and measure the model's performance parameters. These parameters reflect the operating characteristics of the wind turbine blades, such as aerodynamic performance (e.g., efficiency, flow rate) and noise levels. The target performance parameters mainly focus on two key points: the performance of the wind turbine blades (e.g., efficiency, flow rate) and the noise generated by the wind turbine blades. Based on these target performance parameters, a multi-objective optimization function is constructed. This multi-objective optimization function is a mathematical expression that the optimization algorithm attempts to maximize or minimize, reflecting the goals the designer wants to achieve through optimization. The multi-objective optimization function aims to optimize the performance of the wind turbine blades while considering noise control.

[0097] Design unit 30 is used to solve the Pareto solution of the multi-objective optimization function through a multi-objective genetic algorithm, obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0098] Specifically, a multi-objective genetic algorithm is a heuristic optimization device used to handle problems with multiple competing or complementary optimization objectives. In this embodiment, the multi-objective optimization function includes multiple objectives such as the aerodynamic performance and noise control of the wind turbine blades. The multi-objective genetic algorithm searches for and identifies solutions that achieve a good balance across multiple objectives by simulating natural selection and genetic processes, such as selection, crossover, and mutation. The NSGA-II (Non-dominated Sorting Genetic Algorithm II) algorithm is used as the specific implementation of the multi-objective genetic algorithm. This algorithm maintains the diversity of the population through non-dominated sorting and crowding calculation, and iterates step by step. In each generation, individuals in the population (i.e., the wind turbine blade design) are selected and evolved based on their performance in the multi-objective optimization function space, thereby approximating the Pareto optimal solution set and obtaining the target parameter values ​​of the wind turbine blade model.

[0099] This embodiment obtains initial parameters, constructs a fan blade model based on these parameters, acquires the target performance parameters of the fan blade model, and constructs a multi-objective optimization function based on these parameters. The target performance parameters represent the fan's performance. A multi-objective genetic algorithm is used to solve the multi-objective optimization function to obtain the target parameter values ​​of the fan blade model. The fan blades are then designed based on these target parameter values. Compared to existing technologies where the design of air conditioning fan blades relies heavily on the designer's experience, this application automatically obtains the target parameter values ​​of the fan blade model by establishing a fan blade model and a multi-objective optimization function, and then solving the multi-objective optimization function using a multi-objective genetic algorithm. Therefore, it solves the problem of low optimization efficiency caused by the reliance on manual experience in fan blade design in existing technologies, and improves the optimization efficiency of the blade structure.

[0100] In the specific implementation process, the above step S201, obtaining initial parameters and constructing a wind turbine blade model based on the initial parameters, can be achieved through the following steps: Step S2011: Obtain the angle parameters and dimension parameters of the wind turbine blade to obtain the initial parameters, wherein the angle parameters represent the installation angle of the blade, and the dimension parameters represent the size of the blade; Step S2012: Construct a three-dimensional model based on the initial parameters to obtain the wind turbine blade model. This device constructs the wind turbine blade model through the above steps, which facilitates the simulation of the actual structure of the wind turbine blade and the corresponding performance, and makes it easier to determine the optimal structural parameters.

[0101] Specifically, in designing axial flow fan blades, the first step is to collect and determine some basic design parameters, mainly including angle parameters and dimensional parameters. Angle parameters focus on the blade's installation angle, which determines the relative relationship between the blade and the airflow direction, directly affecting airflow guidance and blade efficiency. Dimensional parameters involve the overall size and specific geometry of the blade, such as its thickness, length, and curvature. These dimensional parameters collectively shape the blade's shape, thus affecting its mechanical performance and hydrodynamic behavior. Based on these initial parameters, a three-dimensional model is constructed to obtain the fan blade model. Having the angle and dimensional parameters, these abstract values ​​are then converted into a concrete three-dimensional model. The three-dimensional model not only visually represents the blade's appearance and structure but also serves as the foundation for further research and analysis. For example, using professional computer-aided design (CAD) software, the angle and dimensional parameters are used as input, and the software's modeling tools and parametric design functions generate a three-dimensional geometric model of the fan blade for subsequent hydrodynamic analysis and performance evaluation.

[0102] In some optional implementations, step S202, obtaining the target performance parameters of the wind turbine blade model and constructing a multi-objective optimization function based on the target performance parameters, can be achieved through the following steps: Step S2021: Obtain the airflow parameters, power parameters, and noise parameters of the wind turbine blade model to obtain the target performance parameters, wherein the airflow parameter represents the airflow generated by the wind turbine blade model, the power parameter represents the power of the wind turbine blade model, and the noise parameter represents the noise of the wind turbine blade model; Step S2022: Construct the multi-objective optimization function with the objectives of maximizing the airflow parameter, minimizing the power parameter, and minimizing the noise parameter. This device, through the above steps, seeks blade designs that exhibit excellent aerodynamic performance, energy consumption, and acoustic performance, thereby meeting the comprehensive requirements of modern industry for high performance, low energy consumption, and low noise in wind turbine blades.

[0103] Specifically, a crucial step in designing axial fan blades is evaluating their performance under actual operating conditions. This includes acquiring airflow parameters (the amount of airflow generated by the blades), power parameters (the energy consumed during blade operation), and noise parameters (the acoustic effects produced during blade operation). These parameters collectively constitute the target performance parameters, which are key indicators for evaluating the quality of the blade design. These parameters are typically obtained through experimental testing or numerical simulation, such as computational fluid dynamics (CFD) analysis. The multi-objective optimization function is set to simultaneously maximize airflow parameters, minimize power parameters, and minimize noise parameters. That is, the goal of design optimization is to ensure high airflow output while minimizing required power and operating noise, achieving a highly efficient, energy-saving, and low-noise fan blade design. Then, optimization algorithms, such as the aforementioned NSGA-II, are used to search for and identify design schemes that achieve the optimal balance among the three objectives of airflow, power, and noise.

[0104] In some alternative implementations, step S203, by solving the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, can be achieved through the following steps: Step S2031: Using the initial parameters as the initial population parameters of the multi-objective genetic algorithm, wherein the initial population parameters represent a set of initial values ​​for the multi-objective genetic algorithm; Step S2032: An iterative step, obtaining the iteration step size and iteration number of the multi-objective genetic algorithm, and iteratively calculating the initial population parameters according to the iteration step size and iteration number to obtain new population parameters, wherein the new population parameters represent a set of new structural parameters obtained by iterative calculation of the initial parameters of the wind turbine blade; Step S2033: Calculating the multi-objective optimization function value corresponding to each new population parameter until the multi-objective optimization function value satisfies the iteration exit condition of the multi-objective genetic algorithm, exiting the multi-objective genetic algorithm, and determining the target parameter value as the multi-objective optimization function value, wherein the iteration exit condition includes at least the current iteration number being greater than or equal to the iteration number. The device obtains the target parameter values ​​of the optimal wind turbine blade model through the above steps. This allows it to find a balance point among multiple target performance parameters and automatically solve for the optimal solution, making blade structure optimization more efficient.

[0105] Specifically, the initial design parameters of the wind turbine blade angle and dimensions are used as the initial state of the genetic algorithm population, and iterative improvement is achieved through the algorithm's genetic mechanism. The iteration step size and number of iterations are crucial parameters in MOGA (Multi-Objective Genetic Algorithm), controlling the search range and depth. The iteration step size determines the magnitude of parameter changes in each generation, while the number of iterations limits the total cycle of the algorithm. In each iteration, the algorithm performs selection, crossover, and mutation operations to generate a new population. Selection is based on the fitness of individuals in the current population, i.e., their performance on the multi-objective optimization function; crossover and mutation operations are used to generate new combinations of design parameters to achieve better performance. Iterative computation creates a new population by updating parameter values, with each individual representing a set of possible wind turbine blade design parameters. These parameters, through iterative processing by the algorithm, gradually approach design points that perform well across multiple objectives such as airflow, power, and noise. For each individual in the new population, its corresponding airflow, power, and noise parameters are calculated using numerical simulation devices such as CFD, thus determining its position in the multi-objective optimization function space. An iteration exit condition is the criterion for terminating the algorithm's execution. This includes at least one condition: the current iteration count must be greater than or equal to a preset iteration count. This means that when the algorithm reaches the preset iteration count, the iteration process will stop regardless of whether an absolutely optimal solution has been found. Setting an iteration exit condition is to prevent the algorithm from getting stuck in an endless loop, and it also serves as effective management of computational resources and time. Generally, when the maximum number of iterations is reached, the individuals in the population are close enough to the optimization objective that an optimal or satisfactory solution can be selected.

[0106] In some optional implementations, step S2033 can be achieved through the following steps: meshing the wind turbine blade model to obtain a meshed wind turbine blade model; and using fluid dynamics software to calculate the multi-objective optimization function values ​​corresponding to the new population parameters of the meshed wind turbine blade model. This device, through the above steps and with the aid of fluid dynamics software, can efficiently calculate the performance indicators of the blade design in terms of airflow, power, and noise, thereby facilitating the selection of a design scheme with superior performance.

[0107] Specifically, before performing any type of fluid dynamics analysis, the three-dimensional model of the wind turbine blade needs to be divided into numerous small units, i.e., a mesh. Meshing discretizes the continuous fluid domain, allowing fluid dynamics equations to be applied to each mesh unit, thus enabling the solution of complex fluid dynamics problems using numerical methods. Specialized fluid dynamics software (such as ANSYS Fluent, CFX, StarCCM+, etc.) is used to simulate the blade's performance under aerodynamic forces, including calculating performance indicators such as airflow, required power, and noise generated by the blade. In the software, the meshed wind turbine blade model is first imported, and then boundary conditions, fluid properties, and solution parameters are set. The software solves the fluid dynamics equations based on the established physical model and numerical methods, obtaining performance data for the blade design. This data is then used to calculate the multi-objective optimization function values ​​corresponding to the new population parameters, i.e., the quantitative expression of optimization objectives such as airflow, power, and noise, providing necessary feedback for the multi-objective genetic algorithm.

[0108] In some optional implementations, step S2032 can be achieved through the following steps: Step S2034: Adjust the parameters of the initial population according to the iteration step size to obtain a progeny population; Step S2035: Merge the progeny population with the initial population to obtain a merged population; Step S2036: Filter the parameters in the merged population to obtain the parameters of the new population. This device performs iterative calculations through the above steps. Through multiple iterations, the algorithm can explore the design space and identify design schemes that demonstrate balanced or superior performance across multiple objectives such as airflow, power, and noise, thereby significantly improving the performance and efficiency of wind turbine blade design.

[0109] Specifically, the iteration step size determines the magnitude of population parameter changes in the genetic algorithm. During optimization, the algorithm fine-tunes the parameters in the initial population according to the iteration step size, generating new parameter combinations through genetic operations such as crossover and mutation, thus producing the offspring population. After generating the offspring population, the algorithm merges these newly generated individuals with the current initial population to form a larger merged population. The merged population includes the current best individual and newly explored individuals, providing a wider range of design samples for subsequent selection, crossover, and mutation. Selection is a crucial step in the genetic algorithm. Based on the individual's performance on the multi-objective optimization function, it retains those with better performance through a selection mechanism while eliminating those with poor performance. The selection process ensures that the population evolves towards the optimization objective. The selection process typically includes steps such as non-dominated sorting and calculating crowding distance. Non-dominated sorting is used to identify individuals that are not dominated by other individuals on any objective, i.e., Pareto optimal individuals; crowding distance calculation is used to maintain the diversity of individuals on the Pareto front. Based on these evaluations, the algorithm selects a certain number of individuals to form a new population, which will be used for the next round of iterative computation.

[0110] In some optional implementations, step S2036 can be achieved by the following steps: calculating the crowding degree of a parameter in the merged population, wherein the crowding degree represents the distance between two parameters; and determining the parameter as the new population parameter if the crowding degree is greater than a preset threshold. This device, by calculating the crowding degree of individuals in the merged population and determining individuals with crowding degrees higher than a preset threshold as new population parameters, can preserve population diversity and avoid premature convergence.

[0111] Specifically, crowding is an indicator used in multi-objective optimization to measure the density of an individual's distribution within the multi-objective optimization function space. It reflects the distance between individuals across multi-objective optimization function values, i.e., the differences in multi-objective performance such as airflow, power, and noise resulting from different combinations of design parameters. Crowding is typically calculated based on an individual's ranking position in each multi-objective optimization function and the differences in multi-objective optimization function values ​​between individuals. For each multi-objective optimization function, the algorithm calculates the neighbor differences between individuals and then sums them across all multi-objective optimization functions to obtain the total crowding of the individuals. In merging populations, individuals with higher crowding—that is, those farther from their neighbors in the multi-objective optimization function space—are more likely to be selected as members of the new population. A preset threshold is a criterion used to select individuals, helping the algorithm identify design parameter combinations with unique performance advantages while maintaining population diversity.

[0112] The wind turbine blade design device includes a processor and a memory. The first building unit, the second building unit, and the design unit are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0113] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can improve the optimization efficiency of the wind turbine blade structure.

[0114] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0115] This invention provides a computer-readable storage medium including a stored program, wherein the program, when running, controls the device containing the computer-readable storage medium to execute the design method for the wind turbine blades.

[0116] Specifically, the design methods for wind turbine blades include:

[0117] Step S201: Obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade.

[0118] Specifically, initial parameters form the basis of the wind turbine blade geometry, including but not limited to the blade installation angle, leading and trailing edge angle, chord length, bend angle, sweep height, and installation angle. These initial parameters are used to model the wind turbine blades. By setting parameters such as chord length and bend angle, different blade shapes can be generated.

[0119] Step S202: Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance;

[0120] Specifically, after establishing the physical model of the wind turbine blades, the next step is to determine and measure the model's performance parameters. These parameters reflect the operating characteristics of the wind turbine blades, such as aerodynamic performance (e.g., efficiency, flow rate) and noise levels. The target performance parameters mainly focus on two key points: the performance of the wind turbine blades (e.g., efficiency, flow rate) and the noise generated by the wind turbine blades. Based on these target performance parameters, a multi-objective optimization function is constructed. This multi-objective optimization function is a mathematical expression that the optimization algorithm attempts to maximize or minimize, reflecting the goals the designer wants to achieve through optimization. The multi-objective optimization function aims to optimize the performance of the wind turbine blades while considering noise control.

[0121] Step S203: Solve the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0122] This invention provides a processor for running a program, wherein the program executes the design method for the wind turbine blades.

[0123] Specifically, the design methods for wind turbine blades include:

[0124] Step S201: Obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade.

[0125] Specifically, initial parameters form the basis of the wind turbine blade geometry, including but not limited to the blade installation angle, leading and trailing edge angle, chord length, bend angle, sweep height, and installation angle. These initial parameters are used to model the wind turbine blades. By setting parameters such as chord length and bend angle, different blade shapes can be generated.

[0126] Step S202: Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance;

[0127] Specifically, after establishing the physical model of the wind turbine blades, the next step is to determine and measure the model's performance parameters. These parameters reflect the operating characteristics of the wind turbine blades, such as aerodynamic performance (e.g., efficiency, flow rate) and noise levels. The target performance parameters mainly focus on two key points: the performance of the wind turbine blades (e.g., efficiency, flow rate) and the noise generated by the wind turbine blades. Based on these target performance parameters, a multi-objective optimization function is constructed. This multi-objective optimization function is a mathematical expression that the optimization algorithm attempts to maximize or minimize, reflecting the goals the designer wants to achieve through optimization. The multi-objective optimization function aims to optimize the performance of the wind turbine blades while considering noise control.

[0128] Step S203: Solve the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0129] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0130] Step S201: Obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade.

[0131] Specifically, initial parameters form the basis of the wind turbine blade geometry, including but not limited to the blade installation angle, leading and trailing edge angle, chord length, bend angle, sweep height, and installation angle. These initial parameters are used to model the wind turbine blades. By setting parameters such as chord length and bend angle, different blade shapes can be generated.

[0132] Step S202: Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance;

[0133] Specifically, after establishing the physical model of the wind turbine blades, the next step is to determine and measure the model's performance parameters. These parameters reflect the operating characteristics of the wind turbine blades, such as aerodynamic performance (e.g., efficiency, flow rate) and noise levels. The target performance parameters mainly focus on two key points: the performance of the wind turbine blades (e.g., efficiency, flow rate) and the noise generated by the wind turbine blades. Based on these target performance parameters, a multi-objective optimization function is constructed. This multi-objective optimization function is a mathematical expression that the optimization algorithm attempts to maximize or minimize, reflecting the goals the designer wants to achieve through optimization. The multi-objective optimization function aims to optimize the performance of the wind turbine blades while considering noise control.

[0134] Step S203: Solve the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0135] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0136] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0137] Step S201: Obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade.

[0138] Specifically, initial parameters form the basis of the wind turbine blade geometry, including but not limited to the blade installation angle, leading and trailing edge angle, chord length, bend angle, sweep height, and installation angle. These initial parameters are used to model the wind turbine blades. By setting parameters such as chord length and bend angle, different blade shapes can be generated.

[0139] Step S202: Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance;

[0140] Specifically, after establishing the physical model of the wind turbine blades, the next step is to determine and measure the model's performance parameters. These parameters reflect the operating characteristics of the wind turbine blades, such as aerodynamic performance (e.g., efficiency, flow rate) and noise levels. The target performance parameters mainly focus on two key points: the performance of the wind turbine blades (e.g., efficiency, flow rate) and the noise generated by the wind turbine blades. Based on these target performance parameters, a multi-objective optimization function is constructed. This multi-objective optimization function is a mathematical expression that the optimization algorithm attempts to maximize or minimize, reflecting the goals the designer wants to achieve through optimization. The multi-objective optimization function aims to optimize the performance of the wind turbine blades while considering noise control.

[0141] Step S203: Solve the Pareto solution of the multi-objective optimization function using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

[0142] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0148] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0149] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0151] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0152] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0153] 1) In the wind turbine blade design method of this application, initial parameters are obtained, a wind turbine blade model is constructed based on the initial parameters, target performance parameters of the wind turbine blade model are obtained, and a multi-objective optimization function is constructed based on the target performance parameters. The target performance parameters are parameters representing the performance of the wind turbine. The multi-objective optimization function is solved using a multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and the wind turbine blade is designed based on the target parameter values. Compared with the prior art, where the design of air conditioning wind turbine blades mainly relies on the experience of designers, this application automatically obtains the target parameter values ​​of the wind turbine blade model by establishing a wind turbine blade model and a multi-objective optimization function, and solving the multi-objective optimization function using a multi-objective genetic algorithm. Therefore, it can solve the problem of low optimization efficiency of blade structure caused by the reliance on manual experience in the design of wind turbine blades in the prior art, and improve the optimization efficiency of blade structure.

[0154] 2) In the fan blade design device of this application, initial parameters are obtained, a fan blade model is constructed based on the initial parameters, target performance parameters of the fan blade model are obtained, and a multi-objective optimization function is constructed based on the target performance parameters. The target performance parameters are parameters representing the fan performance. The multi-objective optimization function is solved using a multi-objective genetic algorithm to obtain the target parameter values ​​of the fan blade model, and the fan blade is designed based on the target parameter values. Compared with the prior art, where the design of air conditioning fan blades mainly relies on the designer's experience, this application automatically obtains the target parameter values ​​of the fan blade model by establishing a fan blade model and a multi-objective optimization function, and solving the multi-objective optimization function using a multi-objective genetic algorithm. Therefore, it can solve the problem of low optimization efficiency of the blade structure caused by the reliance on manual experience in the design of fan blades in the prior art, and improve the optimization efficiency of the blade structure.

[0155] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for designing wind turbine blades, characterized in that, include: Obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade; Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance; The Pareto solution of the multi-objective optimization function is obtained by solving the multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, and the wind turbine blade is designed based on the target parameter values.

2. The method according to claim 1, characterized in that, Obtaining initial parameters and constructing a wind turbine blade model based on the initial parameters includes: The initial parameters are obtained by acquiring the angle parameters and size parameters of the wind turbine blades, wherein the angle parameters are parameters representing the installation angle of the blades, and the size parameters are parameters representing the size of the blades; A three-dimensional model is constructed based on the initial parameters to obtain the wind turbine blade model.

3. The method according to claim 1, characterized in that, Obtain the target performance parameters of the wind turbine blade model, and construct a multi-objective optimization function based on the target performance parameters, including: The air volume parameter, power parameter, and noise parameter of the wind turbine blade model are obtained to obtain the target performance parameter, wherein the air volume parameter represents the air volume generated by the wind turbine blade model, the power parameter represents the power of the wind turbine blade model, and the noise parameter represents the noise of the wind turbine blade model; The multi-objective optimization function is constructed with the objectives of maximizing the air volume parameter, minimizing the power parameter, and minimizing the noise parameter.

4. The method according to claim 1, characterized in that, The Pareto solution of the multi-objective optimization function is obtained by solving the multi-objective genetic algorithm to obtain the target parameter values ​​of the wind turbine blade model, including: The initial parameters are used as the initial population parameters of the multi-objective genetic algorithm, wherein the initial population parameters represent a set of initial values ​​for the multi-objective genetic algorithm; The iterative step involves obtaining the iteration step size and iteration number of the multi-objective genetic algorithm, and iteratively calculating the initial population parameters based on the iteration step size and iteration number to obtain new population parameters, wherein the new population parameters represent a new set of structural parameters obtained by iterative calculation of the initial parameters of the wind turbine blade; Calculate the multi-objective optimization function value corresponding to each of the new population parameters until the multi-objective optimization function value satisfies the iteration exit condition of the multi-objective genetic algorithm, then exit the multi-objective genetic algorithm, and determine the target parameter value as the multi-objective optimization function value, wherein the iteration exit condition includes at least the current iteration number being greater than or equal to the iteration number.

5. The method according to claim 4, characterized in that, Calculate the multi-objective optimization function value corresponding to each of the new population parameters, including: The wind turbine blade model is meshed to obtain a meshed wind turbine blade model; The multi-objective optimization function values ​​corresponding to the new population parameters of the gridded wind turbine blade model are calculated using fluid dynamics software.

6. The method according to claim 4, characterized in that, The initial population parameters are iteratively calculated based on the iteration step size and the number of iterations to obtain new population parameters, including: The parameters of the initial population are adjusted according to the iteration step size to obtain the offspring population; The offspring population is merged with the initial population to obtain a merged population; The parameters of the merged population are filtered to obtain the parameters of the new population.

7. The method according to claim 6, characterized in that, The parameters of the merged population are filtered to obtain the parameters of the new population, including: Calculate the crowding degree of the parameters in the merged population, where the crowding degree represents the distance between two parameters; If the crowding level is greater than a preset threshold, the parameter is determined to be the parameter of the new population.

8. A design device for wind turbine blades, characterized in that, include: The first construction unit is used to obtain initial parameters and construct a wind turbine blade model based on the initial parameters, wherein the initial parameters are parameters representing the initial structure of the wind turbine blade, and the wind turbine blade model is a physical model of the wind turbine blade. The second construction unit is used to obtain the target performance parameters of the wind turbine blade model and construct a multi-objective optimization function based on the target performance parameters, wherein the target performance parameters are parameters representing the wind turbine performance; The design unit is used to solve the Pareto solution of the multi-objective optimization function through a multi-objective genetic algorithm, obtain the target parameter values ​​of the wind turbine blade model, and design the wind turbine blade based on the target parameter values.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the wind turbine blade design method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for designing wind turbine blades according to any one of claims 1 to 7.

Images