Wind power blade static test method, device and equipment and storage medium
The loading capacity in the static test of wind power blades is optimized through genetic algorithms, which solves the problems of low manual adjustment efficiency and overload load, and realizes a more efficient and reliable test solution, ensuring the safety of the blades.
Patent Information
- Application Number
- CN202411224230.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-26
AI Technical Summary
In the static test of existing wind power blades, manual adjustment of load capacity is inefficient and the optimal solution cannot be guaranteed, resulting in overloading of the test load and may cause engineering safety problems.
Genetic algorithm is used to determine the loading force of each loading point in the static test of wind power blades. By obtaining the target bending moment after removing the self-weight influence of each section, a static test scheme of the loading point is randomly generated, and iterated to convergence to output the optimization scheme.
It improves the efficiency of the design test plan and the reliability of the blade test plan, ensures that the deviation between the test bending moment and the design load is minimized, avoids load overload, and enhances engineering safety.
Smart Images

Figure CN119026372A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of wind turbine blade testing, and in particular to a method, a device, an electronic device and a computer-readable storage medium for static testing of wind turbine blades. Background Art
[0002] Wind turbine blades are key components of wind turbine equipment. Their structural strength is crucial to the overall safety and reliability of the wind turbine. Newly developed blades or blades with major process changes must be subjected to full-scale static testing to verify the static strength reserve of the blades. In the current process of designing static loading schemes, engineers use the trial-matching method, that is, manually and empirically adjust the loading force at each loading point to make the cross-sectional bending moment of the tested blade as consistent as possible with the bending moment under the extreme working condition. This method of manually adjusting the loading force is inefficient and cannot be guaranteed to be the optimal solution, resulting in the test load being overloaded relative to the design load during the actual test, which may cause engineering safety issues. Summary of the invention
[0003] The purpose of the present invention is to provide a static testing method, device, electronic device and computer-readable storage medium for wind turbine blades, which are applied to the field of wind turbine blade testing. The method determines the loading force of each loading point in the optimal static test through a genetic algorithm. Compared with the manual determination of the loading force, the efficiency of the test design and the reliability of the blade test plan are improved based on the genetic algorithm.
[0004] In order to solve the above technical problems, the present invention provides a static test method for a wind turbine blade, comprising:
[0005] Obtain the target bending moment of each section of the wind turbine blade after removing the influence of deadweight, and determine the loading points on the wind turbine blade for static testing;
[0006] Randomly generate a preset number of static test schemes for the loading points within a preset loading force value range, and determine the test bending moment of each cross section under each static test scheme;
[0007] Taking the minimum deviation between the test bending moment and the target bending moment of each cross section as the goal, iterating the static test scheme based on a genetic algorithm until convergence, and outputting the optimized static test scheme;
[0008] A static test is performed at the loading point based on the optimized static test scheme to obtain a static test result.
[0009] Optionally, the static force test scheme of randomly generating a preset number of the loading points within a preset loading force value range includes:
[0010] Generate a population matrix with the number of rows being the number of the loading points and the number of columns being the preset number; each column in the population matrix represents one of the static test schemes, and the elements in the column represent the loading force of the loading point in the static test scheme;
[0011] Randomly generate values within a preset load force value range to fill the elements in the population matrix to construct the static test plan.
[0012] Optionally, the step of iterating the static test scheme based on a genetic algorithm until convergence with the goal of minimizing the deviation between the test bending moment of each cross section and the target bending moment, and outputting the optimized static test scheme includes:
[0013] Determining the adaptability of each of the static test schemes based on the test bending moment and the target bending moment of each of the cross sections;
[0014] Updating the candidate optimal solution to the static test solution with the best fitness;
[0015] Reselect the static test scheme based on the fitness to construct the population matrix;
[0016] The elements of each column in the population matrix are encoded and then connected in series to obtain series data;
[0017] Crossing, mutating, de-concatenating and decoding the serial data in each column of the population matrix to obtain a new population matrix;
[0018] The step of determining the test bending moment of each cross section under each static test scheme is restarted until the genetic algorithm converges, and the candidate optimal scheme is determined as the optimized static test scheme.
[0019] Optionally, determining the adaptability of each of the static test schemes based on the test bending moment and the target bending moment of each of the cross sections includes:
[0020] Determine the deviation between the test bending moment and the target bending moment of each cross section under each static test scheme;
[0021] determining an overload boundary and a penalty coefficient of the deviation degree, and when the deviation degree exceeds the overload boundary, correcting the deviation degree based on the penalty coefficient;
[0022] The fitness of each of the static test solutions is calculated based on the deviation and the fitness function.
[0023] Optionally, the fitness function is a standard deviation function.
[0024] Optionally, reselecting the static test scheme based on the fitness to construct the population matrix includes:
[0025] The static test scheme is reselected based on the fitness through a roulette wheel selection method to construct the population matrix.
[0026] Optionally, encoding the elements of each column in the population matrix and then concatenating them to obtain concatenated data includes:
[0027] The elements of each column in the population matrix are binary-coded and then connected in series to obtain series data.
[0028] In order to solve the above technical problems, the present invention provides a wind turbine blade static test device, comprising:
[0029] The first module is used to obtain the target bending moment of each section of the wind turbine blade after removing the influence of its own weight, and determine the loading point on the wind turbine blade for static testing;
[0030] The second module is used to randomly generate a static test scheme for a preset number of the loading points within a preset loading force value range, and determine the test bending moment of each of the cross sections under each of the static test schemes;
[0031] The third module is used to iterate the static test scheme based on a genetic algorithm until convergence with the goal of minimizing the deviation between the test bending moment of each cross section and the target bending moment, and output the optimized static test scheme;
[0032] The fourth module is used to perform a static test at the loading point based on the optimized static test scheme to obtain a static test result.
[0033] In order to solve the above technical problems, the present invention provides an electronic device, comprising:
[0034] Memory, for storing computer programs;
[0035] A processor is used to implement the wind turbine blade static test method when executing the computer program.
[0036] In order to solve the above technical problems, the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the wind turbine blade static test method is implemented.
[0037] It can be seen that the method of the present invention determines the loading points on the wind turbine blade for static testing by obtaining the target bending moment of each section of the wind turbine blade after removing the influence of deadweight; randomly generates static test schemes with a preset number of loading points within a preset load force value range, and determines the test bending moment of each section under each static test scheme; with the goal of minimizing the deviation between the test bending moment of each section and the target bending moment, the static test scheme is iterated based on the genetic algorithm until convergence, and the optimized static test scheme is output; static testing is performed at the loading point based on the optimized static test scheme to obtain static test results. The method of the present invention determines the loading force of each loading point in the optimal static test through a genetic algorithm. Compared with the method of manually determining the loading force, the efficiency of designing the test scheme and the reliability of the blade test scheme based on the genetic algorithm are improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] 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.
[0039] Figure 1 A flow chart of a static testing method for a wind turbine blade provided by an embodiment of the present invention;
[0040] Figure 2 This is a structural block diagram of a wind turbine blade static test device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0041] 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.
[0042] Wind turbine blades are key components of wind turbine equipment. Their structural strength is crucial to the overall safety and reliability of the wind turbine. Newly developed blades or blades with major process changes must be subjected to full-scale static testing to verify the static strength reserve of the blades. The accuracy of the blade static loading method is of great significance to ensure the quality of the blades. At present, the multi-point loading method is usually used for blade static testing, that is, concentrated force loads at multiple loading points are used to make the cross-sectional bending moment of the tested blade fit the target cross-sectional bending moment as closely as possible.
[0043] As wind turbine blades become longer and longer, the static test load of the blades becomes larger. In order to ensure that the blades can safely pass the static test, more loading points need to be applied at the same time to reduce the single loading force while making the cross-sectional bending moment of the blades better fit the target bending moment. In the process of designing the static loading scheme, engineers use the trial matching method, that is, empirically adjusting the loading force of each loading point to make the cross-sectional bending moment of the tested blade as consistent as possible with the extreme working condition bending moment. As wind turbine blades become larger, more and more loading points are required. The method of adjusting the loading force based on experience is less efficient and cannot be guaranteed to be the optimal solution.
[0044] In the process of designing static loading schemes, engineers often empirically adjust the loading force to make the cross-sectional bending moment of the blade under test fit the bending moment of the extreme working condition. When there are more and more loading points, this design method will be more cumbersome and inefficient. In addition, the static test loading force scheme adjusted manually deviates greatly from the optimal scheme, and cannot ensure that the deviation between the test bending moment and the design load is minimized during the static test. As a result, the test load is overloaded relative to the design load during the actual test, which may cause engineering safety problems.
[0045] The following combination Figure 1 , Figure 1 A flowchart of a static test method for a wind turbine blade provided by an embodiment of the present invention, the method may include:
[0046] S101: Obtain the target bending moment of each cross section of the wind turbine blade after removing the influence of deadweight, and determine the loading point on the wind turbine blade for static testing.
[0047] This embodiment can obtain the target bending moment of each section of the wind turbine blade after removing the influence of its own weight, and the target bending moment can be the design load of the wind turbine blade. Due to the influence of its own gravity, the blade self-weight section bending moment is generated, so the target bending moment obtained in this embodiment can be the design load after removing the influence of the self-weight section bending moment.
[0048] Furthermore, this embodiment can determine the loading points on the wind turbine blade for static testing. This embodiment does not limit the method for determining the positions and numbers of the loading points, which can be set based on actual applications and can generally be selected through manual experience. The positions of the loading points in this embodiment should avoid structural danger points.
[0049] S102: Randomly generate static test schemes with a preset number of loading points within a preset loading force value range, and determine the test bending moment of each section under each static test scheme.
[0050] This embodiment can be iterated through a genetic algorithm to obtain the optimal static test scheme, so it is necessary to pre-generate an initial population for iteration. The individuals in the population are a static test scheme in this embodiment, and each static test scheme contains a set of loading forces at loading points.
[0051] This embodiment does not limit the specific method of generating a static test solution. Generally, a static test solution with a preset number of loading points can be randomly generated within a preset load force value range. This embodiment limits the value of the randomly generated loading force by a preset load force range. This embodiment does not limit the specific setting method of the preset load force range, which can generally be set to 0-300kN.
[0052] This embodiment can construct a population in the form of a population matrix. Specifically, this embodiment can generate a population matrix with the number of rows being the number of loading points and the number of columns being a preset number; each column in the population matrix represents a static test scheme, and the elements in the column represent the loading force of the loading point in the static test scheme; values are randomly generated within the preset loading force value range to fill the elements in the population matrix to construct a static test scheme.
[0053] In this embodiment, after the static test scheme is constructed, the test bending moment of each section of the wind turbine blade under each static test scheme can be determined. This embodiment does not limit the specific method of determining the test bending moment. Generally, the loading force of each static test scheme can be used as input and obtained through calculation formula or software simulation, which can be specifically set based on the actual application scenario.
[0054] S103: With the goal of minimizing the deviation between the test bending moment of each section and the target bending moment, the static test plan is iterated based on the genetic algorithm until convergence, and the optimized static test plan is output.
[0055] This embodiment can take minimizing the deviation between the test bending moment of each section and the target bending moment as the goal, iterate the static test plan based on the genetic algorithm until convergence, and output the optimized static test plan.
[0056] Specifically, the present embodiment can first determine the fitness of each static test scheme based on the test bending moment and the target bending moment of each section. The present embodiment does not limit the specific method of calculating the fitness of each static test scheme. The fitness in the present embodiment can be the deviation between the test bending moment and the target bending moment. For example, the fitness in the present embodiment can be the standard deviation between the test bending moment and the target bending moment of each section, that is, the fitness function can be a standard deviation function. In the present embodiment, the smaller the fitness, the more the static test scheme is considered to be in line with the optimal scheme.
[0057] In the process of calculating the fitness of each static test scheme, this embodiment can first determine the deviation between the test bending moment and the target bending moment of each section under each static test scheme. The calculation method of the deviation in this embodiment can be shown as follows:
[0058] ;
[0059] In the formula, is the deviation of the jth section of the wind turbine blade under the i-th static test scheme, is the test bending moment of the jth section of the wind turbine blade under the i-th static test scheme, is the target bending moment of the jth section of the wind turbine blade under the i-th static test scheme.
[0060] In order to eliminate individuals with poor fitness, this embodiment can introduce an overload boundary and a penalty coefficient. When the calculated deviation exceeds the overload boundary, the elimination rate of individuals with poor fitness is increased by the penalty coefficient. That is, this embodiment can determine the overload boundary and penalty coefficient of the deviation. When the deviation exceeds the overload boundary, the deviation is corrected based on the penalty coefficient. This embodiment does not limit the setting range of the overload boundary, nor does it limit the specific value of the penalty coefficient. It can be set based on actual application. Generally, the overload boundary can be set to 0-0.1, and the value of the penalty coefficient can be greater than 1. This embodiment can correct the deviation by directly multiplying the penalty coefficient by the deviation.
[0061] After the deviation correction is completed, this embodiment can calculate the fitness of each static test scheme based on the deviation and the fitness function. The fitness function can be shown as follows:
[0062] ;
[0063] In the formula, is the fitness of the ith static test scheme, m is the number of sections of the wind turbine blade, is the deviation of the j-th section of the wind turbine blade under the i-th static test scheme.
[0064] This embodiment can update the candidate optimal solution to the static test solution with the best fitness, that is, this embodiment can use the static test solution with the smallest fitness as the candidate optimal solution. When there are multiple static test solutions and the fitness calculated are all the smallest, this embodiment can randomly select the candidate optimal solution from the static test solution with the smallest fitness.
[0065] In this embodiment, after the selection of the optimal candidate solution is completed, it can be considered that one iteration of the genetic algorithm is completed. In this embodiment, the static test solution can be reselected based on fitness to perform crossover and mutation to generate a new static test solution for the next round of genetic algorithm iteration.
[0066] Specifically, when the static test scheme is represented by a population matrix, this embodiment can reselect the static test scheme based on fitness to construct the population matrix, encode the elements of each column in the population matrix and then concatenate them to obtain concatenated data, cross, mutate, de-concatenate and decode the concatenated data in each column of the population matrix to obtain a new population matrix, and each column in the new population matrix is a newly constructed static test scheme.
[0067] This embodiment does not limit the specific method of reselecting static test schemes based on fitness to construct a population matrix. Generally, the static test schemes can be reselected based on fitness through a roulette selection method to construct a population matrix. Specifically, the selection probability of each static test scheme is obtained by fitness calculation, and the static test schemes are reselected based on the selection probability through a roulette selection method to construct a population matrix.
[0068] This embodiment does not limit the specific encoding method. Generally, the elements of each column in the population matrix can be binary-encoded and then connected in series to obtain series data. Accordingly, the encoded binary data needs to be converted into decimal data during the decoding process. This embodiment does not limit the number of bits after each element is encoded, which can generally be unified as eight bits. For example, the decimal value 2 can be 00000010 after binary encoding. The specific number of bits can be set based on the application.
[0069] This embodiment does not limit the specific method of crossover mutation, and can be selected from the crossover mutation methods of existing genetic algorithms based on actual application scenarios. Specifically, crossover can be randomly selecting two coded static test schemes, truncating and exchanging them at the same preset coding position; mutation can be randomly selecting an encoded static test scheme, and reversely transforming it at a random position, that is, converting 1 to 0 and converting 0 to 1.
[0070] After constructing a new population matrix, this embodiment can start again from the step of determining the test bending moment of each section under each static test scheme, iterate the genetic algorithm until convergence, and obtain the optimized static test scheme. Specifically, start again from the step of determining the test bending moment of each section under each static test scheme, until the genetic algorithm converges, and determine the candidate optimal scheme as the optimized static test scheme.
[0071] This embodiment does not limit the specific conditions for the genetic algorithm to iterate until convergence, nor does it limit the specific type of the genetic algorithm, which can be set based on actual applications.
[0072] S104: Perform a static test at the loading point based on the optimized static test scheme to obtain a static test result.
[0073] In this embodiment, a static test can be performed at each loading point of the wind turbine blade based on the optimized static test scheme to obtain a static test result under the optimized static test scheme. In this embodiment, if the static test result under the optimized static test scheme does not meet the requirements, the static test scheme can be reconstructed and iterated through a genetic algorithm to obtain the optimized static test scheme again.
[0074] Based on the above embodiments, the method of the present invention determines the optimal loading force of each loading point in the static test through a genetic algorithm. Compared with the method of manually determining the loading force, the efficiency of designing the test plan and the reliability of the blade test plan based on the genetic algorithm are improved.
[0075] The following is a specific embodiment of a static test method for a wind turbine blade provided by the present invention. In this specific embodiment, 96 cross sections of a wind turbine blade can be tested, 8 loading points can be set, the overload boundary can be 0-0.1, the penalty coefficient is greater than 1, the number of iterations of the genetic algorithm is set to 2000, the population size is set to 2000, and the preset loading force range is 0-300kN;
[0076] Step 1: Construct a population matrix with a dimension of 8×2000. Each column in the population matrix represents a static test scheme, and each row represents the loading force of a loading point under different static test schemes. The elements of the population matrix are randomly generated within the preset loading force range.
[0077] Step 2: Calculate the deviation between the test bending moment and the target bending moment of each section under each static test scheme by the following formula:
[0078] ;
[0079] In the formula, is the deviation of the jth section of the wind turbine blade under the i-th static test scheme, is the test bending moment of the jth section of the wind turbine blade under the i-th static test scheme, is the target bending moment of the jth section of the wind turbine blade under the i-th static test scheme;
[0080] Step 3: Multiply the deviation outside the range of 0-0.1 by the penalty coefficient. After the penalty is completed, the fitness of each static test scheme is calculated based on the deviation of each section and the fitness function. The fitness function can be shown as follows:
[0081] ;
[0082] In the formula, is the fitness of the ith static test scheme, m is the number of sections of the wind turbine blade, is the deviation of the jth section of the wind turbine blade under the i-th static test scheme;
[0083] Step 4: Update the candidate optimal solution to the static test solution with the minimum fitness;
[0084] Step 5: Reselect the static test scheme based on the fitness by roulette, and build a new population matrix based on the reselected static test scheme;
[0085] Step 6: Binary encode the elements in the new population matrix, and concatenate the encoded elements in the same column to obtain concatenated data;
[0086] Step 7: Perform crossover and mutation based on the serial data of each column in the new population matrix, and deserialize and decode the serial data after the crossover and mutation are completed;
[0087] Step 8: Restart from step 2 until the number of iterations of the genetic algorithm reaches 2000, and determine the candidate optimal solution after the iteration as the optimized static test solution;
[0088] Step 9: Perform static tests at 8 loading points based on the optimized static test scheme to obtain static test results.
[0089] The following combination Figure 2 , Figure 2 The structural block diagram of a wind turbine blade static test device provided by an embodiment of the present invention may include:
[0090] The first module 100 is used to obtain the target bending moment of each cross section of the wind turbine blade after removing the influence of deadweight, and determine the loading point on the wind turbine blade for static testing;
[0091] The second module 200 is used to randomly generate a preset number of static test schemes for the loading points within a preset loading force value range, and determine the test bending moment of each of the cross sections under each of the static test schemes;
[0092] The third module 300 is used to iterate the static test scheme based on a genetic algorithm until convergence with the goal of minimizing the deviation between the test bending moment of each cross section and the target bending moment, and output the optimized static test scheme;
[0093] The fourth module 400 is used to perform a static test at the loading point based on the optimized static test scheme to obtain a static test result.
[0094] Based on the above embodiments, the method of the present invention determines the optimal loading force of each loading point in the static test through a genetic algorithm. Compared with the method of manually determining the loading force, the efficiency of designing the test plan and the reliability of the blade test plan based on the genetic algorithm are improved.
[0095] Based on the above embodiment, the second module 200 may include:
[0096] The first unit is used to generate a population matrix with a number of rows equal to the number of the loading points and a number of columns equal to the preset number; each column in the population matrix represents one of the static test schemes, and an element in a column represents a loading force of the loading point in the static test scheme;
[0097] The second unit is used to randomly generate values within a preset loading force value range to fill the elements in the population matrix to construct the static test plan.
[0098] Based on the above embodiments, the third module 300 may include:
[0099] A third unit is used to determine the adaptability of each of the static test schemes based on the test bending moment and the target bending moment of each of the cross sections;
[0100] A fourth unit is used for updating the candidate optimal solution to the static test solution with the best fitness;
[0101] A fifth unit is used for reselecting the static test scheme based on the fitness to construct the population matrix;
[0102] A sixth unit is used for encoding the elements of each column in the population matrix and then serializing them to obtain serial data;
[0103] A seventh unit is used for performing crossover, mutation, de-concatenation and decoding on the series data in each column of the population matrix to obtain a new population matrix;
[0104] The eighth unit is used to restart execution from the third unit until the genetic algorithm converges and determine the candidate optimal solution as the optimized static test solution.
[0105] Based on the above embodiments, the third unit may include:
[0106] A first subunit is used to determine the deviation between the test bending moment and the target bending moment of each cross section under each static test scheme;
[0107] A second subunit is used to determine an overload boundary and a penalty coefficient of the deviation degree, and when the deviation degree exceeds the overload boundary, correct the deviation degree based on the penalty coefficient;
[0108] The third subunit is used to calculate the fitness of each static test scheme based on the deviation and the fitness function.
[0109] Based on the above embodiments, the fitness function is a standard deviation function.
[0110] Based on the above embodiments, the fifth unit may include:
[0111] The fourth subunit is used to reselect the static test scheme based on the fitness through a roulette wheel selection method to construct the population matrix.
[0112] Based on the above embodiments, the sixth unit may include:
[0113] The fifth subunit is used to perform binary coding on the elements of each column in the population matrix and then connect them in series to obtain series data.
[0114] Based on the above embodiments, the present invention further provides an electronic device, which may include a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the steps provided in the above embodiments may be implemented. Of course, the device may also include various necessary network interfaces, power supplies, and other components.
[0115] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by an execution terminal or a processor, the method provided in the embodiment of the present invention can be implemented; the storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
[0116] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including 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, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
Claims
1. A static test method for wind turbine blades, characterized in that: include: Obtain the target bending moment of each section of the wind turbine blade after removing the influence of deadweight, and determine the loading points on the wind turbine blade for static testing; Randomly generate a preset number of static test schemes for the loading points within a preset loading force value range, and determine the test bending moment of each cross section under each static test scheme; Taking the minimum deviation between the test bending moment and the target bending moment of each cross section as the goal, iterating the static test scheme based on a genetic algorithm until convergence, and outputting the optimized static test scheme; A static test is performed at the loading point based on the optimized static test scheme to obtain a static test result.
2. The static testing method for wind turbine blades according to claim 1, characterized in that: The static force test scheme of randomly generating a preset number of the loading points within a preset loading force value range includes: Generate a population matrix with the number of rows being the number of the loading points and the number of columns being the preset number; each column in the population matrix represents one of the static test schemes, and the elements in the column represent the loading force of the loading point in the static test scheme; Randomly generate values within a preset load force value range to fill the elements in the population matrix to construct the static test plan.
3. The static testing method for wind turbine blades according to claim 2 is characterized in that: The method aims to minimize the deviation between the test bending moment of each cross section and the target bending moment, iterates the static test scheme based on a genetic algorithm until convergence, and outputs the optimized static test scheme, including: Determining the adaptability of each of the static test schemes based on the test bending moment and the target bending moment of each of the cross sections; Updating the candidate optimal solution to the static test solution with the best fitness; Reselect the static test scheme based on the fitness to construct the population matrix; The elements of each column in the population matrix are encoded and then connected in series to obtain series data; Crossing, mutating, de-concatenating and decoding the serial data in each column of the population matrix to obtain a new population matrix; The step of determining the test bending moment of each cross section under each static test scheme is restarted until the genetic algorithm converges, and the candidate optimal scheme is determined as the optimized static test scheme.
4. The static testing method for wind turbine blades according to claim 3 is characterized in that: The determining the adaptability of each of the static test schemes based on the test bending moment and the target bending moment of each of the cross sections includes: Determine the deviation between the test bending moment and the target bending moment of each cross section under each static test scheme; determining an overload boundary and a penalty coefficient of the deviation degree, and when the deviation degree exceeds the overload boundary, correcting the deviation degree based on the penalty coefficient; The fitness of each of the static test solutions is calculated based on the deviation and the fitness function.
5. The static testing method for wind turbine blades according to claim 4 is characterized in that: The fitness function is a standard deviation function.
6. The static testing method for wind turbine blades according to claim 3, characterized in that: The reselecting the static test scheme based on the fitness to construct the population matrix includes: The static test scheme is reselected based on the fitness through a roulette wheel selection method to construct the population matrix.
7. The static testing method for wind turbine blades according to claim 3, characterized in that: The encoding and concatenating of the elements in each column of the population matrix to obtain the concatenated data comprises: The elements of each column in the population matrix are binary-coded and then connected in series to obtain series data.
8. A static test device for wind turbine blades, characterized in that: include: The first module is used to obtain the target bending moment of each section of the wind turbine blade after removing the influence of its own weight, and determine the loading point on the wind turbine blade for static testing; The second module is used to randomly generate a static test scheme for a preset number of the loading points within a preset loading force value range, and determine the test bending moment of each of the cross sections under each of the static test schemes; The third module is used to iterate the static test scheme based on a genetic algorithm until convergence with the goal of minimizing the deviation between the test bending moment of each cross section and the target bending moment, and output the optimized static test scheme; The fourth module is used to perform a static test at the loading point based on the optimized static test scheme to obtain a static test result.
9. An electronic device, characterized in that: include: Memory, for storing computer programs; A processor, configured to implement the wind turbine blade static testing method as claimed in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the wind turbine blade static testing method according to any one of claims 1 to 7 is implemented.
