Design optimization method and device for wind turbine blades, storage medium and electronic equipment

Abstract

The present invention provides a design optimization method and device for wind turbine blades, a storage medium and an electronic device, the method comprising: generating an initial blade population, including a plurality of initial individuals; each initial individual represents a set of blade structural parameters; based on the optimization target and the genetic optimization algorithm, iteratively optimizing the blade population to obtain an optimized blade population, including a plurality of optimized individuals; the optimization target is to maximize power generation and minimize blade load; determine the power generation and blade root load of each optimized individual, and use the power generation and blade root load of the optimized individual as its fitness; determine the best individual among the optimized individuals according to the optimization target and the fitness of the optimized individual; use the blade structural parameters corresponding to the best individual as the blade optimization design scheme. By applying the method of the present invention, the optimization of blade structural parameters can be automatically completed, and the optimization design scheme can be obtained without manual design operation, which can improve the optimization efficiency and the optimization effect.

Description

Technical Field

[0001] The present invention relates to the field of simulation technology, and in particular to a design optimization method and device for a wind turbine blade, a storage medium and an electronic device. Background Art

[0002] Wind turbine blades are one of the core components of wind turbines (i.e. wind turbine generators). The design of the blades directly affects the performance and power generation efficiency of the wind turbine. In the design process of wind turbine blades, the optimization goals are usually to increase power generation and reduce load, and the design parameters of the blades are continuously optimized.

[0003] At present, the aerodynamic design and structural design of the blades are usually carried out first. After the blade design is completed, relevant personnel simulate the whole machine based on the current blade design scheme, calculate the power generation and load under the current blade design scheme, and then manually adjust the structural parameters of the blade according to the calculation results of the power generation and load. Then, simulation is carried out according to the new blade design scheme to calculate the corresponding power generation and load. The optimization is iterated in this way until a blade design scheme that meets the requirements is obtained.

[0004] Based on the existing blade design optimization method, it is necessary to manually simulate the whole machine, calculate data and adjust blade parameters repeatedly. The optimization of design parameters depends on the personal experience of the staff. The entire optimization process usually takes a lot of time and it is difficult to obtain the optimal solution, which makes the efficiency of wind turbine blade design optimization low and the design optimization effect poor. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a design optimization method for wind turbine blades to solve the problem that the design optimization method for wind turbine blades requires manual repetition of multiple operations, and relevant personnel design blade parameters based on experience, resulting in low overall design optimization efficiency and poor optimization effect.

[0006] The embodiment of the present invention also provides a design optimization device for wind turbine blades to ensure the actual implementation and application of the above method.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] A design optimization method for a wind turbine blade, comprising:

[0009] Generate an initial leaf population, the initial leaf population comprising a plurality of initial individuals; each of the initial individuals represents a set of leaf structure parameters;

[0010] Based on a preset optimization goal and a preset genetic optimization algorithm, the initial blade population is iteratively optimized to obtain an optimized blade population; the optimized blade population includes a plurality of optimized individuals; the optimization goal is to maximize the power generation of the wind turbine and minimize the blade load;

[0011] For each of the optimized individuals, determining the power generation and blade root load corresponding to the optimized individual, and using the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual;

[0012] Determining the best individual in the optimized leaf population according to the optimization target and the fitness of each of the optimized individuals;

[0013] The blade structural parameters corresponding to the best individuals in the optimized blade population are used as the optimized design scheme for the wind turbine blades.

[0014] Optionally, the above method, based on a preset optimization target and a preset genetic optimization algorithm, iteratively optimizes the initial leaf population to obtain an optimized leaf population, including:

[0015] When entering a current iteration cycle of the iterative optimization process, determining an initial population corresponding to the current iteration cycle;

[0016] For each individual in the initial population, calling a preset blade design software, so that the blade design software generates a blade model corresponding to the individual based on the blade structural parameters corresponding to the individual;

[0017] According to the leaf model corresponding to each individual in the initial population, determine whether each individual in the initial population meets the preset constraint condition, take the individuals meeting the constraint condition as candidate individuals, and form a candidate population from each candidate individual;

[0018] For each candidate individual, based on the blade model corresponding to the candidate individual, the power generation and blade root load corresponding to the candidate individual are calculated, and the power generation and blade root load corresponding to the candidate individual are used as the fitness of the candidate individual;

[0019] Based on the optimization target and the fitness of each candidate individual, each preferred individual in the candidate population is determined through the genetic mechanism of the genetic optimization algorithm, and each offspring individual is generated based on each preferred individual;

[0020] Merging each of the preferred individuals and each of the offspring individuals, and using the merged population as the optimized population corresponding to the current iteration cycle;

[0021] Determine whether the current iteration cycle meets the preset iteration termination condition, and if the current iteration cycle does not meet the iteration termination condition, enter the next iteration cycle;

[0022] If the current iteration cycle meets the iteration termination condition, the iterative optimization process is terminated, and the optimized leaf population is determined based on the optimized population corresponding to the current iteration cycle;

[0023] Among them, if the current iteration cycle is the first iteration cycle, the initial population corresponding to the current iteration cycle is the initial leaf population; if the current iteration cycle is not the first iteration cycle, the initial population corresponding to the current iteration cycle is the optimized population corresponding to the previous iteration cycle.

[0024] In the above method, optionally, judging whether each individual in the initial population meets a preset constraint condition based on the leaf model corresponding to each individual in the initial population includes:

[0025] For each individual in the initial population, the blade model in the preset constraint condition file is replaced with the blade model corresponding to the individual to obtain the constraint condition calculation file corresponding to the individual;

[0026] For each individual in the initial population, calling a preset constraint calculation software, and causing the constraint calculation software to calculate the constraint condition corresponding to the individual based on the constraint condition calculation file corresponding to the individual;

[0027] For each individual in the initial population, determine whether the constraint conditions corresponding to the individual meet the preset constraint setting conditions. If the constraint conditions corresponding to the individual meet the constraint setting conditions, then the individual is determined to meet the constraint conditions. If the constraint conditions corresponding to the individual do not meet the constraint setting conditions, then the individual is determined to not meet the constraint conditions.

[0028] In the above method, optionally, the step of calculating the power generation and blade root load corresponding to the candidate individual based on the blade model corresponding to the candidate individual includes:

[0029] The blade model corresponding to the candidate individual is used to replace the blade model in the preset target operating condition file to obtain the whole machine operating condition file corresponding to the candidate individual;

[0030] Calling preset load calculation software to enable the load calculation software to calculate the power generation and blade root load corresponding to the whole machine operation condition file;

[0031] The power generation and blade root load calculated by the load calculation software are used as the power generation and blade root load corresponding to the candidate individual.

[0032] The above method, optionally, based on the optimization target and the fitness of each candidate individual, determines each preferred individual in the candidate population through the genetic mechanism of the genetic optimization algorithm, and generates each offspring individual based on each preferred individual, including:

[0033] Based on the optimization target and the fitness of each candidate individual, determining each preferred individual in the candidate population by a preset fast non-dominated sorting method;

[0034] Determine a plurality of parent individuals from each of the preferred individuals by using a preset tournament competition algorithm;

[0035] A crossover mutation operation is performed on each of the parent individuals, and the generated new individuals are used as the child individuals.

[0036] The above method may optionally further include:

[0037] In the initial population corresponding to the current iteration cycle, the individuals that do not meet the constraint conditions are regarded as individuals to be excluded;

[0038] The preset fitness threshold is used as the fitness corresponding to each of the individuals to be excluded, so as to exclude each of the individuals to be excluded in the iterative optimization process.

[0039] In the above method, optionally, the determining whether the current iteration cycle meets a preset iteration termination condition includes:

[0040] Determine the number of iterations corresponding to the current iteration cycle;

[0041] Determining whether the number of iterations reaches a preset iteration number threshold;

[0042] If the number of iterations does not reach the iteration number threshold, determining that the current iteration cycle does not meet the iteration termination condition;

[0043] If the number of iterations has reached the iteration number threshold, it is determined that the current iteration cycle meets the iteration termination condition.

[0044] A design optimization device for a wind turbine blade, comprising:

[0045] A population generation unit, used to generate an initial leaf population, wherein the initial leaf population includes a plurality of initial individuals; each of the initial individuals represents a set of leaf structure parameters;

[0046] An iterative optimization unit, for iteratively optimizing the initial blade population based on a preset optimization target and a preset genetic optimization algorithm to obtain an optimized blade population; the optimized blade population includes a plurality of optimized individuals; the optimization target is to maximize the power generation of the wind turbine and minimize the blade load;

[0047] A first determination unit is used to determine, for each of the optimized individuals, the power generation and blade root load corresponding to the optimized individual, and use the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual;

[0048] A second determination unit, configured to determine the best individual in the optimized leaf population according to the optimization target and the fitness of each of the optimized individuals;

[0049] The third determining unit is used to use the blade structural parameters corresponding to the best individual in the optimized blade population as the optimized design scheme of the wind turbine blade.

[0050] A storage medium comprises stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned design optimization method for wind turbine blades.

[0051] An electronic device comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to implement the above-mentioned method for optimizing the design of a wind turbine blade.

[0052] A design optimization method for wind turbine blades provided based on the above-mentioned embodiment of the present invention includes: generating an initial blade population, wherein the initial blade population includes multiple initial individuals; each initial individual represents a set of blade structural parameters; based on a preset optimization target and a preset genetic optimization algorithm, iteratively optimizing the initial blade population to obtain an optimized blade population; the optimized blade population includes multiple optimized individuals; the optimization target is to maximize the power generation of the wind turbine and minimize the blade load; for each optimized individual, determining the power generation and blade root load corresponding to the optimized individual, and using the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual; determining the optimal individual in the optimized blade population according to the optimization target and the fitness of each optimized individual; and using the blade structural parameters corresponding to the optimal individual in the optimized blade population as the optimized design scheme for the wind turbine blades. By applying the method provided in the embodiment of the present invention, the blade structural parameters that need to be optimized can be used as individual characteristics to generate a blade population including multiple initial individuals, and the maximum power generation and the minimum blade load can be used as optimization goals. Through the genetic optimization algorithm, iterative optimization is performed on the basis of the initial blade population to obtain the optimal individual, so as to determine the design scheme of the wind turbine blade. That is, the genetic optimization algorithm can be used to automatically optimize the structural parameters of the blade to obtain the optimal combination of structural parameters. There is no need to manually perform multiple operations such as whole machine simulation, data calculation and blade parameter adjustment, which is conducive to improving the efficiency of optimization design. The optimization adjustment of the blade parameters is obtained by iterative optimization of the algorithm, which is conducive to obtaining the actual optimal solution and can improve the design optimization effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0054] Figure 1 A method flow chart of a method for designing and optimizing a wind turbine blade provided by an embodiment of the present invention;

[0055] Figure 2 Another method flow chart of a method for design optimization of a wind turbine blade provided by an embodiment of the present invention;

[0056] Figure 3 A schematic diagram of a design optimization process of a wind turbine blade provided by an embodiment of the present invention;

[0057] Figure 4 A schematic diagram of an optimization result provided by an embodiment of the present invention;

[0058] Figure 5 A schematic structural diagram of a wind turbine blade design optimization device provided by an embodiment of the present invention;

[0059] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0062] The embodiment of the present invention provides a design optimization method for a wind turbine blade. The method can be applied to a wind turbine optimization design platform. The execution subject can be a processor of the platform. The method flow chart of the method is as follows: Figure 1 As shown, including:

[0063] S101: generating an initial leaf population, wherein the initial leaf population includes a plurality of initial individuals; each of the initial individuals represents a set of leaf structure parameters;

[0064] In the method provided by the embodiment of the present invention, the blade design structural parameters that need to be optimized can be preset, for example, the design structural parameters that need to be optimized may include positioning lines and plies. According to the blade design process requirements, the required value range of each type of design structural parameter is set respectively, and then based on each blade design structural parameter and its corresponding value range, the optimization design process of the wind turbine blade is triggered.

[0065] When entering the optimization design process of wind turbine blades, multiple initial individuals can be randomly generated based on various design structural parameters and their corresponding value ranges, and the initial blade population is composed of various initial individuals. It can be understood that each initial individual represents a set of blade structural parameters, that is, a set of values ​​of various design structural parameters that need to be optimized.

[0066] S102: based on a preset optimization target and a preset genetic optimization algorithm, iteratively optimizing the initial blade population to obtain an optimized blade population; the optimized blade population includes a plurality of optimized individuals; the optimization target is to maximize the power generation of the wind turbine and minimize the blade load;

[0067] In the method provided by the embodiment of the present invention, the maximum power generation of the wind turbine and the minimum blade load are used as optimization goals, and a multi-objective iterative optimization is performed on the initial blade population through a preset genetic optimization algorithm. That is, according to the genetic mechanism of the genetic optimization algorithm, on the basis of the initial blade population, individual fitness evaluation, individual selection, crossover mutation and other operations are iteratively performed to continuously update the individuals in the blade population. After completing the iterative optimization process, the final blade population is obtained as the optimized blade population, and the optimized blade population includes multiple optimized individuals. It can be understood that each optimized individual represents a set of blade structural parameters. The genetic optimization algorithm for specific application can be configured based on the existing genetic algorithm.

[0068] S103: for each of the optimized individuals, determining the power generation and blade root load corresponding to the optimized individual, and taking the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual;

[0069] In the method provided in the embodiment of the present invention, the power generation and blade root load generated by the blade design corresponding to each optimized individual can be calculated based on the blade structural parameter group corresponding to the optimized individual, and the power generation and blade root load can be used as the fitness of the corresponding optimized individual. In the specific implementation process, the fitness of the optimized individual may have been calculated in the iterative optimization process, and the fitness result calculated in the iterative optimization process can be directly obtained. For the optimized individual whose fitness has not been calculated, the same principle as in the iterative optimization process can be used to calculate the fitness corresponding to the optimized individual. Regarding the calculation of power generation and blade root load, the calculation can be performed by calling the load calculation software, or by configuring other methods, which does not affect the function of the method provided in the embodiment of the present invention.

[0070] S104: determining the best individual in the optimized leaf population according to the optimization target and the fitness of each optimized individual;

[0071] In the method provided by an embodiment of the present invention, the optimal individual is selected from the optimized blade population according to the optimization target and the fitness of each optimized individual, that is, the individual with the largest corresponding power generation and the smallest corresponding blade load among the optimized individuals.

[0072] S105: Using the blade structural parameters corresponding to the best individual in the optimized blade population as an optimized design scheme for the wind turbine blade.

[0073] In the method provided by the embodiment of the present invention, the blade structure parameter group represented by the optimal individual is used as the optimized blade structure parameter group, that is, the optimization result of this blade design optimization, that is, the optimized design scheme for wind turbine blades.

[0074] Based on the method provided by the embodiment of the present invention, in the process of wind turbine optimization design, an initial blade population can be generated, and the initial blade population includes multiple initial individuals; each initial individual represents a set of blade structural parameters; based on a preset optimization goal and a preset genetic optimization algorithm, the initial blade population is iteratively optimized to obtain an optimized blade population; the optimized blade population includes multiple optimized individuals; the optimization goal is to maximize the power generation of the wind turbine and minimize the blade load; for each optimized individual, the power generation and blade root load corresponding to the optimized individual are determined, and the power generation and blade root load corresponding to the optimized individual are used as the fitness of the optimized individual; according to the optimization goal and the fitness of each optimized individual, the optimal individual in the optimized blade population is determined; the blade structural parameters corresponding to the optimal individual in the optimized blade population are used as the optimization design scheme for wind turbine blades. By applying the method provided in the embodiment of the present invention, the blade structural parameters that need to be optimized can be used as individual characteristics to generate a blade population including multiple initial individuals, and the maximum power generation and the minimum blade load can be used as optimization goals. Through the genetic optimization algorithm, iterative optimization is performed on the basis of the initial blade population to obtain the optimal individual, so as to determine the design scheme of the wind turbine blade. That is, the genetic optimization algorithm can be used to automatically optimize the structural parameters of the blade to obtain the optimal combination of structural parameters. There is no need to manually perform multiple operations such as whole machine simulation, data calculation and blade parameter adjustment, which is conducive to improving the efficiency of optimization design. The optimization adjustment of the blade parameters is obtained by iterative optimization of the algorithm, which is conducive to obtaining the actual optimal solution and can improve the design optimization effect.

[0075] exist Figure 1 Based on the method shown in FIG. 1 , in the method provided in the embodiment of the present invention, as Figure 2 As shown, the process of iteratively optimizing the initial leaf population based on the preset optimization target and the preset genetic optimization algorithm mentioned in step S102 to obtain the optimized leaf population includes:

[0076] S201: Determine the initial population corresponding to the current iteration cycle;

[0077] In the method provided by the embodiment of the present invention, when entering the process of iterative optimization of the initial leaf population, the first iteration cycle of the iterative optimization process will be entered. After completing the processing process of the first iteration cycle, the next iteration cycle will be entered for processing until the iterative optimization process is terminated.

[0078] In the method provided by the embodiment of the present invention, when entering a new iteration cycle, the initial population corresponding to the current iteration cycle can be determined according to the cycle situation of the current iteration cycle. It can be understood that the initial population contains each individual that needs to be iteratively optimized at present, and each individual represents a set of blade structure parameters. Specifically, if the current iteration cycle is the first iteration cycle, then the initial blade population is used as the initial population corresponding to the current iteration cycle. If the current iteration cycle is not the first iteration cycle, the optimized population corresponding to the previous iteration cycle of the current iteration cycle is used as the initial population corresponding to the current iteration cycle. In other words, if the current iteration cycle is the first iteration cycle, the initial population corresponding to the current iteration cycle is the initial blade population. If the current iteration cycle is not the first iteration cycle, the initial population corresponding to the current iteration cycle is the optimized population corresponding to the previous iteration cycle. For the optimized population corresponding to the iteration cycle, please refer to the subsequent description.

[0079] S202: for each individual in the initial population, calling a preset blade design software, and causing the blade design software to generate a blade model corresponding to the individual based on the blade structural parameters corresponding to the individual;

[0080] In the method provided by the embodiment of the present invention, a design file of a blade can be imported in advance, wherein a design model of the blade is configured, that is, a parametric model of the blade, including the appearance information and structural information of the blade. The method provided by the embodiment of the present invention can call a preset blade design software, send the blade structural parameters characterized by each individual in the initial population to the blade design software, trigger the blade design software to generate a corresponding blade model based on the design file of the blade, respectively using the blade structural parameters characterized by each individual, and use the blade model generated based on the blade structural parameters corresponding to the corresponding individual as the blade model corresponding to the individual. Blade design software is an existing software in the field of wind turbine design, which can be used to construct a blade model.

[0081] S203: judging whether each individual in the initial population meets preset constraints according to the leaf model corresponding to each individual in the initial population, taking the individuals meeting the constraints as candidate individuals, and forming a candidate population from each of the candidate individuals;

[0082] In the method provided by the embodiment of the present invention, the constraint conditions can be set in advance according to the constraint conditions of the wind turbine operation. For each individual in the initial population, according to the blade model corresponding to the individual, it is judged whether the blade design realized based on the blade structural parameters corresponding to the individual satisfies the constraint conditions of the whole machine operation, that is, it is judged whether the individual meets the constraint conditions. If the individual meets the constraint conditions, the individual is used as a candidate individual, thereby obtaining the candidate population of the current iteration cycle.

[0083] S204: For each candidate individual, based on the blade model corresponding to the candidate individual, calculate the power generation and blade root load corresponding to the candidate individual, and use the power generation and blade root load corresponding to the candidate individual as the fitness of the candidate individual;

[0084] In the method provided by the embodiment of the present invention, according to the blade model corresponding to each candidate individual, the whole machine operating condition realized based on the blade structural parameters corresponding to the candidate individual is simulated, so as to calculate the power generation and blade root load that can be generated. The power generation and blade root load corresponding to each candidate individual are used as the fitness of the candidate individual.

[0085] S205: Based on the optimization target and the fitness of each candidate individual, determine each preferred individual in the candidate population through the genetic mechanism of the genetic optimization algorithm, and generate each offspring individual based on each preferred individual;

[0086] In the method provided in the embodiment of the present invention, based on the optimization target and the fitness of each candidate individual, a plurality of relatively optimal individuals can be selected from each candidate individual as preferred individuals through the genetic mechanism of the genetic optimization algorithm, and a crossover mutation operation is performed on each current preferred individual to generate each offspring individual. The number of preferred individuals to be selected can be set according to actual needs.

[0087] S206: merging each of the preferred individuals and each of the offspring individuals, and using the merged population as the optimized population corresponding to the current iteration cycle;

[0088] In the method provided by an embodiment of the present invention, each preferred individual in the candidate population in the current iteration cycle and each offspring individual in the current iteration cycle are merged, and the merged population is used as the optimized population for the current iteration cycle, that is, the optimized population contains each preferred individual and each offspring individual in the current candidate population.

[0089] S207: Determine whether the current iteration cycle meets a preset iteration termination condition;

[0090] In the method provided in the embodiment of the present invention, an iteration termination condition may be preset, such as termination upon reaching a predetermined number of iterations or upon satisfying other iteration requirements. According to the preset iteration termination condition, it is determined whether the current iteration cycle meets the termination requirement in the iteration termination condition.

[0091] S208: Entering the next iteration cycle;

[0092] In the method provided by the embodiment of the present invention, if the current iteration cycle does not meet the iteration termination condition, the optimized population corresponding to the current iteration cycle is used as the initial population corresponding to the next iteration cycle, and the optimization process of the next iteration cycle is entered.

[0093] S209: End the iterative optimization process, and determine the optimized leaf population based on the optimized population corresponding to the current iteration cycle;

[0094] In the method provided by the embodiment of the present invention, if the current iteration cycle meets the iteration termination condition, the iterative optimization process is terminated, and the optimized leaf population is determined based on the optimized population corresponding to the current iteration cycle. Specifically, if it can be ensured that each offspring individual meets the preset constraint conditions in the process of generating offspring individuals, the optimized population corresponding to the current iteration cycle can be used as the optimized leaf population. If it cannot be ensured that each offspring individual meets the preset constraint conditions, it is necessary to determine whether each individual in the optimized population corresponding to the current iteration cycle meets the constraint conditions based on the principles in step S202 and step S203, remove the individuals that do not meet the constraint conditions from the population, retain the individuals that meet the constraint conditions, and use the processed population as the optimized leaf population.

[0095] exist Figure 2 On the basis of the method shown, in the method provided by the embodiment of the present invention, the process mentioned in step S203 of judging whether each individual in the initial population meets the preset constraint condition according to the leaf model corresponding to each individual in the initial population includes:

[0096] For each individual in the initial population, the blade model in the preset constraint condition file is replaced with the blade model corresponding to the individual to obtain the constraint condition calculation file corresponding to the individual;

[0097] In the method provided in the embodiment of the present invention, a constraint condition file can be configured according to actual industrial design requirements, and the constraint condition file is provided with constraint conditions for the operation of the entire wind turbine, which may specifically include clearance constraints, standard deviation constraints, angle of attack constraints, and custom constraints. The constraint condition file is a design file required in the design of a wind turbine, and can be used to calculate the constraints of the operation of the wind turbine under corresponding working conditions, wherein a complete machine model including a wind turbine blade model is deployed.

[0098] In the method provided by an embodiment of the present invention, for each individual in the initial population, the blade model in the constraint working condition file can be replaced with the blade model corresponding to the individual, and then the constraint working condition file of the blade model corresponding to the individual is deployed as the constraint working condition calculation file corresponding to the individual.

[0099] For each individual in the initial population, calling a preset constraint calculation software, and causing the constraint calculation software to calculate the constraint condition corresponding to the individual based on the constraint condition calculation file corresponding to the individual;

[0100] In the method provided by the embodiment of the present invention, for each individual in the initial population, the pre-deployed constraint calculation software is called, the constraint calculation software is triggered to apply the constraint condition calculation file, the constraint calculation is performed based on the blade model corresponding to the individual, and the constraint condition calculated by the constraint calculation software is obtained, that is, the various constraint values ​​calculated based on the blade model corresponding to the individual. The constraint calculation software is an existing software in the field of wind turbine design, which can be used to calculate the corresponding constraint conditions during the operation of the whole machine.

[0101] For each individual in the initial population, determine whether the constraint conditions corresponding to the individual meet the preset constraint setting conditions. If the constraint conditions corresponding to the individual meet the constraint setting conditions, then the individual is determined to meet the constraint conditions. If the constraint conditions corresponding to the individual do not meet the constraint setting conditions, then the individual is determined to not meet the constraint conditions.

[0102] In the method provided by the embodiment of the present invention, the constraint setting conditions, that is, the set values ​​of each constraint, can be set in advance according to actual needs. According to the constraint conditions corresponding to each individual in the initial population, it can be judged whether each individual meets the preset constraint setting conditions, that is, when designing the blade based on the blade structural parameters corresponding to the individual, whether the operation of the whole machine meets the various constraints, that is, whether the individual meets the constraint conditions. If the constraint values ​​in the constraint conditions corresponding to the individual are within the range of the corresponding constraint setting values ​​in the constraint setting conditions, it is considered that the individual meets the constraint conditions. If there are constraint values ​​in the constraint conditions of the individual that exceed the range of the corresponding constraint setting values ​​in the constraint setting conditions, it is considered that the individual does not meet the constraint conditions.

[0103] exist Figure 2 On the basis of the method shown, in the method provided by the embodiment of the present invention, the process of calculating the power generation and blade root load corresponding to the candidate individual based on the blade model corresponding to the candidate individual mentioned in step S204 includes:

[0104] The blade model corresponding to the candidate individual is used to replace the blade model in the preset target operating condition file to obtain the whole machine operating condition file corresponding to the candidate individual;

[0105] In the method provided in an embodiment of the present invention, a target operating condition file can be configured according to actual industrial design requirements. The target operating condition file is provided with target conditions for calculating power generation and blade root loads, which can be used to simulate and calculate the power generation and blade root loads generated by the normal operation of the wind turbine under the corresponding wind turbine structure. The target operating condition file is deployed with a whole machine model including a wind turbine blade model.

[0106] In the method provided by an embodiment of the present invention, when calculating the power generation and blade root load corresponding to a candidate individual, the blade model in the target operating condition file can be replaced by the blade model corresponding to the candidate individual, and the target operating condition file of the blade model corresponding to the candidate individual can be deployed as the whole machine operating condition file corresponding to the candidate individual.

[0107] Calling preset load calculation software to enable the load calculation software to calculate the power generation and blade root load corresponding to the whole machine operation condition file;

[0108] In the method provided by the embodiment of the present invention, the pre-deployed load calculation software is called, and the load calculation software is triggered to apply the whole machine operating condition file corresponding to the candidate individual, and calculate the power generation and blade root load based on the blade model corresponding to the candidate individual.

[0109] The power generation and blade root load calculated by the load calculation software are used as the power generation and blade root load corresponding to the candidate individual.

[0110] In the method provided by the embodiment of the present invention, the power generation and blade root load calculated by the load calculation software can be obtained, and the power generation and blade root load are used as the power generation and blade root load corresponding to the candidate individual.

[0111] Based on the method provided in the embodiment of the present invention, during the optimization design process of wind turbine blades, constraint calculation, power generation and blade root load calculation can be performed respectively by calling third-party constraint calculation software and load calculation software, which is beneficial to improving the calculation speed and further improving the optimization efficiency.

[0112] exist Figure 2 On the basis of the method shown in the figure, in the method provided by the embodiment of the present invention, the process mentioned in step S205 of determining each preferred individual in the candidate population based on the optimization target and the fitness of each candidate individual through the genetic mechanism of the genetic optimization algorithm, and generating each offspring individual based on each preferred individual, includes:

[0113] Based on the optimization target and the fitness of each candidate individual, determining each preferred individual in the candidate population by a preset fast non-dominated sorting method;

[0114] In the method provided in the embodiment of the present invention, based on the optimization target and the fitness of the candidate individuals, the candidate individuals of the candidate population are sorted by a fast non-dominated sorting method, and a plurality of individuals ranked first are selected in order as preferred individuals, and the number of preferred individuals can be configured according to actual needs. The fast non-dominated sorting method is an existing genetic algorithm and will not be described in detail here.

[0115] Determine a plurality of parent individuals from each of the preferred individuals by using a preset tournament competition algorithm;

[0116] A crossover mutation operation is performed on each of the parent individuals, and the generated new individuals are used as the child individuals.

[0117] In the method provided by the embodiment of the present invention, a tournament competition algorithm is used to select multiple individuals from each preferred individual to compete, and multiple relatively optimal individuals are selected as parent individuals. Crossover operations and mutation operations are performed on each parent individual to generate new individuals, and each newly generated individual is used as each child individual.

[0118] Based on the method provided by the embodiment of the present invention, based on the fast non-dominated sorting method and the tournament competition algorithm, the operations of individual selection and crossover mutation are implemented, which is conducive to improving the convergence of the genetic algorithm and improving the solution efficiency.

[0119] exist Figure 2 On the basis of the method shown, the method provided in the embodiment of the present invention further includes:

[0120] In the initial population corresponding to the current iteration cycle, the individuals that do not meet the constraint conditions are regarded as individuals to be excluded;

[0121] In the method provided by the embodiment of the present invention, in the process of judging whether each individual in the initial population meets the preset constraint conditions, if there is an individual that does not meet the constraint conditions, the individual is regarded as an individual to be excluded.

[0122] The preset fitness threshold is used as the fitness corresponding to each of the individuals to be excluded, so as to exclude each of the individuals to be excluded in the iterative optimization process.

[0123] In the method provided by the embodiment of the present invention, the fitness of each individual to be excluded is configured with a preset fitness threshold, that is, the fitness corresponding to each individual to be excluded is the preset fitness threshold. The preset fitness threshold represents a fitness that will not be selected, so as to exclude each individual to be excluded in the iterative optimization process. In the iterative optimization process, the individual will not be selected for inheritance and will be excluded.

[0124] exist Figure 2Based on the method shown, in the method provided by the embodiment of the present invention, the process of determining whether the current iteration cycle meets the preset iteration termination condition mentioned in step S207 includes:

[0125] Determine the number of iterations corresponding to the current iteration cycle;

[0126] In the method provided by the embodiment of the present invention, after entering the iterative optimization process, the current number of iterations can be accumulated when the processing process of each iteration cycle is completed by means of a counter, etc. The number of iterations of the current iteration cycle can be determined by recording the current number of iterations.

[0127] Determining whether the number of iterations reaches a preset iteration number threshold;

[0128] In the method provided in the embodiment of the present invention, the iteration number threshold can be set in advance according to actual needs. The iteration number corresponding to the current iteration cycle is compared with the preset iteration number threshold. If the current iteration number is less than the iteration number threshold, the current iteration number does not reach the iteration number threshold. If the current iteration number is not less than the iteration number threshold, the current iteration number has reached the iteration number threshold.

[0129] If the number of iterations does not reach the iteration number threshold, determining that the current iteration cycle does not meet the iteration termination condition;

[0130] If the number of iterations has reached the iteration number threshold, it is determined that the current iteration cycle meets the iteration termination condition.

[0131] In the method provided by the embodiment of the present invention, if the current number of iterations does not reach the preset iteration number threshold, it is determined that the current iteration cycle does not meet the preset iteration termination condition; otherwise, it is considered that the current iteration cycle meets the preset iteration termination condition.

[0132] Based on the method provided in the embodiment of the present invention, the number of iterations of the iterative optimization process can be controlled by setting an iteration number threshold, and can be flexibly configured according to actual needs.

[0133] In order to better illustrate the method provided by the embodiment of the present invention, based on the methods provided by the previous embodiments and in combination with actual application scenarios, the embodiment of the present invention provides another design optimization method for wind turbine blades. The method provided by the embodiment of the present invention can be regarded as an optimization method for increasing power and reducing load (increasing power generation and reducing load) of wind turbine blades. The method uses an algorithm to link blade design software, constraint calculation and load calculation software to achieve a complete closed loop of blade design optimization, and uses an improved genetic algorithm to automatically optimize the structural parameters of the blades to find the optimal combination of structural parameters, which is conducive to obtaining a blade design solution that increases the power generation of the unit and reduces the blade load. The method provided by the embodiment of the present invention can be specifically deployed as an optimization design tool.

[0134] In the method provided in the embodiment of the present invention, it is necessary to set the optimization target, optimization variables and constraints. The optimization target is to increase the power generation of the unit and reduce the blade load. The optimization variables are the design structural parameters of the blade, including the positioning line and the ply. The constraints include clearance constraints, standard deviation constraints, angle of attack constraints and custom constraints. The specific constraints can be set according to the optimization requirements.

[0135] Before design optimization, it is necessary to configure the blade design file, target condition file, constraint condition file, control file, wind file and other files required for constraint calculation and load calculation. Select blade optimization variables, set variable ranges, and based on the method provided in the embodiment of the present invention, automatically complete the iteration of blade design optimization and load calculation, optimize the blade structural parameters, and obtain the optimized blade parameter solution set.

[0136] like Figure 3 As shown, the design optimization process of the wind turbine blade provided by the embodiment of the present invention mainly includes:

[0137] S1: According to the blade power increase and load reduction requirements, specify the blade structural parameters c that need to be optimized i , according to the blade design process requirements, set c i The value range of is k1~k2, a leaf structure parameters are randomly generated, and the initial leaf structure population is obtained.

[0138] S2: For each population individual generated by S1, the blade design software is automatically called to calculate the cross-sectional properties, generate a blade model, and replace the blade models in the target operating condition file and the constraint operating condition file with the newly generated blade model to generate a group of new whole machine calculation operating condition files.

[0139] S3: Call the constraint calculation software, apply the whole machine calculation condition file corresponding to each individual, calculate the constraint condition of each population individual, that is, ensure that the individual's constraint condition meets the set constraint requirement D0 (that is, the set value of the constraint) during the optimization process, and judge whether the constraint condition of each individual meets the constraint requirement. If the current individual does not meet the D0 requirement, enter S8, change the fitness of the individual to the preset maximum value, and exclude the current individual.

[0140] S4: If the constraint condition of the individual meets the D0 requirement, start calculating the target condition of the individual, including calculating the power generation x1 and load x2, which are used as the fitness for optimization. The optimization goal is to maximize x1 and minimize x2. Specifically, by calling the load calculation software and applying the individual whole machine calculation condition file, the power generation and load corresponding to the individual are calculated.

[0141] S5: Determine whether the number of iterations is less than the set maximum number of iterations n.

[0142] S6: If the number of iterations is less than n, and the current iteration cycle is the first, then the fast non-dominated sorting method is used to perform fast non-dominated sorting on each individual in the population according to the goal of large power generation x1 and small load x2, and m optimal individuals are selected from them, and then a championship competition is carried out to generate a parent individuals, and each parent individual is cross-mutated to generate a child individuals. Then return to step S2 and enter the next iteration cycle. If the number of iterations is less than n, and the current iteration cycle is not the first, the current a child individuals (i.e., the child individuals generated in the previous cycle) and the m optimal individuals selected in the previous cycle are merged, and fast non-dominated sorting is performed according to the goal of large power generation x1 and small load x2, and the m optimal individuals of the current cycle are selected, and then a championship competition is carried out to generate a parent individuals, and each parent individual is cross-mutated to generate a child individuals. Then enter S2, and repeat the cycle until the iterative optimization process ends.

[0143] S7: When the number of iterations is greater than the set maximum value n, the optimization ends and the optimization solution set is output, from which the optimal blade individual is obtained, that is, the blade individual with high power generation and small load obtained by optimization, and the blade structural parameter group represented by the blade individual is used as the optimization design scheme of the blade.

[0144] Among them, the structural optimization parameter c of the blade iIt mainly involves positioning lines and plies. The parameters of the blade design file are located through the positioning lines and ply names, and then the optimization range k1~k2 is given. The optimization process of the blade can be realized automatically, including the call of the blade design software, the call of the target working condition and the whole machine calculation of the constraint working condition. The target working condition includes load calculation and power generation calculation, among which the load calculation can be a combination of multiple working conditions, and the goal is to reduce the maximum limit load of the blade root in all working conditions. There are two types of power generation calculation, one is static power generation calculation, which has fast calculation speed and low accuracy, and the other is dynamic power generation calculation, which has slow calculation speed and high accuracy. Different projects can be selected according to efficiency and accuracy. Constraint working conditions can also be a combination of multiple working conditions, requiring each working condition to meet the set constraint value. When selecting working conditions, the possible extreme load conditions of the blade can be enveloped as much as possible to improve the optimization accuracy of the blade.

[0145] Based on the method provided by the embodiment of the present invention, a wind turbine blade is simulated to adjust the structural parameters of the blade to increase power generation and reduce load, and the blade is optimized for weight reduction. This verification mainly optimizes the positioning line and ply of the blade main beam and web. A total of 15 groups of optimization variables are selected. According to the design requirements of the blade, a reasonable variable range is given. The optimization objectives include reducing the blade root M xy The limit load increases the power generation of the whole machine. The working condition is dlc1.5ba-1. The working condition is to calculate the dynamic power generation. The wind speed range is 3 to 20m / s. The constraint condition is dlc1.5ad-11, and the clearance constraint is required to be no less than 5m. After the input preparation is completed, the platform starts to automatically optimize the blades. The optimization results are as follows Figure 4 As shown in the figure, the horizontal axis is the power generation, the vertical axis is the blade root load, the red star mark is the initial blade, and the green scattered points are the optimized blade individuals. The ID12 blade is selected. The performance achieved based on the blade structural parameters characterized by this blade increases the power generation by 6 hours. The blade root M xy The load was reduced by 2.8% and the blade weight was reduced by 1 t.

[0146] Based on the method provided by the embodiment of the present invention, the blade design software and the load calculation software can be linked to realize a complete closed loop of blade design optimization, and improve the iteration efficiency of blade power increase and load reduction optimization. By using the improved genetic algorithm to automatically optimize the blade structural parameters, a large number of structural parameter combinations with high power generation, small load and light weight can be found, which is conducive to achieving blade weight reduction, load reduction and power increase.

[0147] and Figure 1 Corresponding to the design optimization method of a wind turbine blade shown in FIG. 1 , an embodiment of the present invention further provides a design optimization device for a wind turbine blade, for optimizing Figure 1 The specific implementation of the method shown in is shown in the structural diagram Figure 5 As shown, including:

[0148] The population generation unit 301 is used to generate an initial leaf population, wherein the initial leaf population includes a plurality of initial individuals; each of the initial individuals represents a set of leaf structure parameters;

[0149] The iterative optimization unit 302 is used to iteratively optimize the initial blade population based on a preset optimization target and a preset genetic optimization algorithm to obtain an optimized blade population; the optimized blade population includes a plurality of optimized individuals; the optimization target is to maximize the power generation of the wind turbine and minimize the blade load;

[0150] A first determining unit 303 is used to determine, for each of the optimized individuals, the power generation and blade root load corresponding to the optimized individual, and use the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual;

[0151] A second determining unit 304 is used to determine the best individual in the optimized leaf population according to the optimization target and the fitness of each of the optimized individuals;

[0152] The third determining unit 305 is used to use the blade structural parameters corresponding to the best individual in the optimized blade population as the optimized design scheme of the wind turbine blade.

[0153] exist Figure 5 Based on the device shown, the device provided by the embodiment of the present invention can be further expanded into multiple units. The function of each unit can be found in the description of each embodiment provided in the previous text for the design optimization method of wind turbine blades, and no further examples will be given here.

[0154] By using the device provided by the embodiment of the present invention, the blade structural parameters that need to be optimized can be used as individual characteristics to generate a blade population including multiple initial individuals, and the maximum power generation and the minimum blade load can be used as optimization goals. Through the genetic optimization algorithm, iterative optimization is performed on the basis of the initial blade population to obtain the optimal individual, so as to determine the design scheme of the wind turbine blade. That is, the genetic optimization algorithm can be used to automatically optimize the structural parameters of the blade to obtain the optimal combination of structural parameters. There is no need to manually perform multiple operations such as whole machine simulation, data calculation and blade parameter adjustment, which is conducive to improving the efficiency of optimization design. The optimization adjustment of the blade parameters is obtained by iterative optimization of the algorithm, which is conducive to obtaining the actual optimal solution and can improve the design optimization effect.

[0155] An embodiment of the present invention further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned wind turbine blade design optimization method.

[0156] The embodiment of the present invention further provides an electronic device, the structural diagram of which is shown in FIG. Figure 6 As shown, it specifically includes a memory 401 and one or more instructions 402, wherein the one or more instructions 402 are stored in the memory 401 and are configured to be executed by one or more processors 403 to perform the following operations:

[0157] Generate an initial leaf population, the initial leaf population comprising a plurality of initial individuals; each of the initial individuals represents a set of leaf structure parameters;

[0158] Based on a preset optimization goal and a preset genetic optimization algorithm, the initial blade population is iteratively optimized to obtain an optimized blade population; the optimized blade population includes a plurality of optimized individuals; the optimization goal is to maximize the power generation of the wind turbine and minimize the blade load;

[0159] For each of the optimized individuals, determining the power generation and blade root load corresponding to the optimized individual, and using the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual;

[0160] Determining the best individual in the optimized leaf population according to the optimization target and the fitness of each of the optimized individuals;

[0161] The blade structural parameters corresponding to the best individuals in the optimized blade population are used as the optimized design scheme for the wind turbine blades.

[0162] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0163] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0164] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A design optimization method for a wind turbine blade, characterized in that: include: generating an initial leaf population, wherein the initial leaf population includes a plurality of initial individuals; Each of the initial individuals represents a set of blade structural parameters; Based on a preset optimization target and a preset genetic optimization algorithm, iteratively optimizing the initial leaf population to obtain an optimized leaf population; The optimized blade population includes a plurality of optimized individuals; the optimization goal is to maximize the power generation of the wind turbine and minimize the blade load; For each of the optimized individuals, determining the power generation and blade root load corresponding to the optimized individual, and using the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual; Determining the best individual in the optimized leaf population according to the optimization target and the fitness of each of the optimized individuals; Using the blade structural parameters corresponding to the best individual in the optimized blade population as an optimized design scheme for the wind turbine blade; The iterative optimization of the initial leaf population based on a preset optimization target and a preset genetic optimization algorithm to obtain an optimized leaf population includes: When entering a current iteration cycle of the iterative optimization process, determining an initial population corresponding to the current iteration cycle; For each individual in the initial population, calling a preset blade design software, so that the blade design software generates a blade model corresponding to the individual based on the blade structural parameters corresponding to the individual; According to the leaf model corresponding to each individual in the initial population, determine whether each individual in the initial population meets the preset constraint condition, take the individuals meeting the constraint condition as candidate individuals, and form a candidate population from each candidate individual; For each candidate individual, based on the blade model corresponding to the candidate individual, the power generation and blade root load corresponding to the candidate individual are calculated, and the power generation and blade root load corresponding to the candidate individual are used as the fitness of the candidate individual; Based on the optimization target and the fitness of each candidate individual, each preferred individual in the candidate population is determined through the genetic mechanism of the genetic optimization algorithm, and each offspring individual is generated based on each preferred individual; Merging each of the preferred individuals and each of the offspring individuals, and using the merged population as the optimized population corresponding to the current iteration cycle; Determine whether the current iteration cycle meets the preset iteration termination condition, and if the current iteration cycle does not meet the iteration termination condition, enter the next iteration cycle; If the current iteration cycle meets the iteration termination condition, the iterative optimization process is terminated, and the optimized leaf population is determined based on the optimized population corresponding to the current iteration cycle; Among them, if the current iteration cycle is the first iteration cycle, the initial population corresponding to the current iteration cycle is the initial leaf population; if the current iteration cycle is not the first iteration cycle, the initial population corresponding to the current iteration cycle is the optimized population corresponding to the previous iteration cycle.

2. The design optimization method for wind turbine blades according to claim 1, characterized in that: The step of judging whether each individual in the initial population meets a preset constraint condition based on the leaf model corresponding to each individual in the initial population includes: For each individual in the initial population, the blade model in the preset constraint condition file is replaced with the blade model corresponding to the individual to obtain the constraint condition calculation file corresponding to the individual; For each individual in the initial population, calling a preset constraint calculation software, and causing the constraint calculation software to calculate the constraint condition corresponding to the individual based on the constraint condition calculation file corresponding to the individual; For each individual in the initial population, determine whether the constraint conditions corresponding to the individual meet the preset constraint setting conditions. If the constraint conditions corresponding to the individual meet the constraint setting conditions, then the individual is determined to meet the constraint conditions. If the constraint conditions corresponding to the individual do not meet the constraint setting conditions, then the individual is determined to not meet the constraint conditions.

3. The design optimization method for wind turbine blades according to claim 1, characterized in that: The step of calculating the power generation and blade root load corresponding to the candidate individual based on the blade model corresponding to the candidate individual includes: The blade model corresponding to the candidate individual is used to replace the blade model in the preset target operating condition file to obtain the whole machine operating condition file corresponding to the candidate individual; Calling preset load calculation software to enable the load calculation software to calculate the power generation and blade root load corresponding to the whole machine operation condition file; The power generation and blade root load calculated by the load calculation software are used as the power generation and blade root load corresponding to the candidate individual.

4. The design optimization method for wind turbine blades according to claim 1, characterized in that: The method of determining each preferred individual in the candidate population based on the optimization target and the fitness of each candidate individual through the genetic mechanism of the genetic optimization algorithm, and generating each offspring individual based on each preferred individual, comprises: Based on the optimization target and the fitness of each candidate individual, determining each preferred individual in the candidate population by a preset fast non-dominated sorting method; Determine a plurality of parent individuals from each of the preferred individuals by using a preset tournament competition algorithm; A crossover mutation operation is performed on each of the parent individuals, and the generated new individuals are used as the child individuals.

5. The design optimization method for wind turbine blades according to claim 1, characterized in that: Also includes: In the initial population corresponding to the current iteration cycle, the individuals that do not meet the constraint conditions are regarded as individuals to be excluded; The preset fitness threshold is used as the fitness corresponding to each of the individuals to be excluded, so as to exclude each of the individuals to be excluded in the iterative optimization process.

6. The design optimization method for wind turbine blades according to claim 1, characterized in that: The determining whether the current iteration cycle meets a preset iteration termination condition includes: Determine the number of iterations corresponding to the current iteration cycle; Determining whether the number of iterations reaches a preset iteration number threshold; If the number of iterations does not reach the iteration number threshold, determining that the current iteration cycle does not meet the iteration termination condition; If the number of iterations has reached the iteration number threshold, it is determined that the current iteration cycle meets the iteration termination condition.

7. A design optimization device for a wind turbine blade, characterized in that: include: A population generation unit, used to generate an initial leaf population, wherein the initial leaf population includes a plurality of initial individuals; Each of the initial individuals represents a set of blade structural parameters; An iterative optimization unit, used for iteratively optimizing the initial leaf population based on a preset optimization target and a preset genetic optimization algorithm to obtain an optimized leaf population; The optimized blade population includes a plurality of optimized individuals; the optimization goal is to maximize the power generation of the wind turbine and minimize the blade load; A first determination unit is used to determine, for each of the optimized individuals, the power generation and blade root load corresponding to the optimized individual, and use the power generation and blade root load corresponding to the optimized individual as the fitness of the optimized individual; A second determination unit, configured to determine the best individual in the optimized leaf population according to the optimization target and the fitness of each of the optimized individuals; A third determination unit is used to use the blade structural parameters corresponding to the best individual in the optimized blade population as an optimized design scheme for the wind turbine blade; Wherein, the iterative optimization unit is specifically used for: when entering the current iteration cycle of the iterative optimization process, determining the initial population corresponding to the current iteration cycle; for each individual in the initial population, calling the preset blade design software, so that the blade design software generates the blade model corresponding to the individual based on the blade structural parameters corresponding to the individual; judging whether each individual in the initial population meets the preset constraints according to the blade model corresponding to each individual in the initial population, taking the individuals meeting the constraints as candidate individuals, and forming a candidate population from each of the candidate individuals; for each of the candidate individuals, calculating the power generation and blade root load corresponding to the candidate individual based on the blade model corresponding to the candidate individual, and taking the power generation and blade root load corresponding to the candidate individual as the fitness of the candidate individual; based on the optimization target and the fitness of each of the candidate individuals, through the genetic optimization algorithm The genetic mechanism is used to determine each preferred individual in the candidate population, and each offspring individual is generated based on each preferred individual; each preferred individual and each offspring individual is merged, and the merged population is used as the optimized population corresponding to the current iteration cycle; whether the current iteration cycle meets the preset iteration termination condition is determined, if the current iteration cycle does not meet the iteration termination condition, then the next iteration cycle is entered; if the current iteration cycle meets the iteration termination condition, then the iterative optimization process is terminated, and the optimized leaf population is determined based on the optimized population corresponding to the current iteration cycle; wherein, if the current iteration cycle is the first iteration cycle, the initial population corresponding to the current iteration cycle is the initial leaf population, and if the current iteration cycle is not the first iteration cycle, then the initial population corresponding to the current iteration cycle is the optimized population corresponding to the previous iteration cycle.

8. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the design optimization method for wind turbine blades according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The device comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to execute the design optimization method for a wind turbine blade according to any one of claims 1 to 6.

Images