Wind turbine generator basic size optimization method and system

Abstract

The invention provides a wind turbine generator foundation size optimization method and system, and relates to the technical field of wind turbine generators, and the method specifically comprises the steps: S1, taking a plurality of wind turbine generator foundations as samples to form a sample set, and collecting the attribute parameters and environmental load parameters of each sample in the sample set; s2, carrying out data processing on the environmental load parameters, generating correction coefficients, and obtaining corrected attribute parameters; s3, carrying out data processing on the corrected attribute parameters, generating objective functions of basic cost, deformation and stability, respectively optimizing the objective functions to obtain a first optimized value, and simultaneously generating and optimizing a comprehensive objective function to obtain a second optimized value; and S4, comparing the difference between the first optimization value and the second optimization value, comparing the difference with a preset difference threshold value, and judging whether the optimization meets the expectation or not. According to the method, the environmental load is comprehensively considered, the accuracy and reliability of the optimization result are improved, and the balance and the optimal standard of the design in all aspects are ensured through multi-target comprehensive optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine generator systems, and in particular to a method and system for optimizing the foundation size of a wind turbine generator system. Background Art

[0002] As a clean and renewable energy source, wind energy has the prospect of large-scale development and utilization, and has attracted more and more attention from the world. The tower supports the weight of the whole machine and provides height for the wind rotor. It is an important part of the wind turbine generator set. The tower foundation is the load-bearing part of the entire tower. Its design and manufacturing level will directly affect the safety and performance of the entire unit. Its safety and economy are particularly important.

[0003] In the prior art, the publication number CN109543287A discloses a method for optimizing the size of a wind turbine foundation based on a genetic algorithm, which includes the following steps: Step 1, determine the coding rules, variable objective function and constraint conditions; Step 2, randomly generate an initial population according to the selected tower foundation size range, and set the initial parameters required by the genetic algorithm: population size N, maximum evolutionary generation Mmax, and crossover mutation probability; Step 3, take the force performance, deformation, and stability of the tower foundation as constraints, set the objective function of the genetic algorithm as the cost of the raw materials of the tower foundation, and calculate the fitness value of the individual; Step 4, use the roulette mechanism to select and retain the best individual, and perform crossover, mutation, and inversion to form a new individual to form a new generation of population; Step 5, repeat steps 3 to 4, and use the parameters corresponding to the maximum fitness value as the final optimization result. This method can reduce the cost of raw materials for the tower foundation while ensuring engineering requirements.

[0004] However, there are still some shortcomings: As can be seen from the above statements, constraints are usually restrictions that must be strictly met during the optimization process, and solutions that violate these conditions are unacceptable. In the feasible solution space that satisfies all constraints, there are a large number of solutions. While these solutions meet the deformation and stability requirements, their costs vary greatly; in addition, although the deformation and stability of the tower foundation have been used as constraints, these constraints only guarantee the minimum design standards, not the optimal standards.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a method and system for optimizing the foundation size of a wind turbine generator set to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for optimizing the size of a wind turbine foundation, comprising the following specific steps:

[0009] S1. Taking multiple wind turbine foundations as samples to form a sample set, and collecting attribute parameters and environmental load parameters of each sample in the sample set, wherein the attribute parameters include the diameter, depth, height and slope of the foundation, and the environmental load parameters include wind pressure, wind speed, wind direction angle, snow depth and snow load;

[0010] S2. Process the wind pressure, wind speed, wind direction angle, snow depth and snow load, and perform correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation, and correct the diameter, depth, height and slope of the wind turbine foundation by the correction coefficients to obtain the corrected diameter, depth, height and slope of the foundation;

[0011] S3. Process the diameter, depth, height and slope of the corrected foundation and perform correlation analysis to generate objective functions of the cost, deformation and stability of the wind turbine foundation, respectively, optimize the objective functions of the cost, deformation and stability of the wind turbine foundation, obtain first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation, process the objective functions of the cost, deformation and stability of the wind turbine foundation to generate a comprehensive objective function, optimize the comprehensive objective function of the wind turbine foundation, and obtain second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation;

[0012] S4. Calculate the first optimized value of the diameter, depth, height and slope of the wind turbine foundation and the second optimized value of the diameter, depth, height and slope of the wind turbine foundation respectively, obtain the respective average optimized difference, compare the respective average optimized difference with the preset difference threshold, judge whether the optimization of the diameter, depth, height and slope meets expectations, and judge whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when achieving the goals of cost, deformation and stability of the wind turbine foundation respectively. If so, an optimal solution is obtained. If the conditions are not met, iterative optimization is required, that is, readjust the parameters and objective function, and perform optimization calculation again until all goals are met.

[0013] Furthermore, the wind pressure, wind speed, wind direction angle, snow depth and snow load are processed and correlated to generate correction coefficients for correcting the basic attribute parameters, based on the following formula:

[0014]

[0015] Where C is the correction coefficient, W iis the wind pressure of the ith sample, P i is the wind speed of the ith sample, V i is the wind direction angle of the i-th sample, S i is the snow load of the ith sample, L i is the snow depth of the i-th sample, i is the index of the sample, and N is the number of samples.

[0016] Furthermore, the diameter, depth, height and slope of the wind turbine foundation are corrected by the correction coefficient to obtain the corrected diameter, depth, height and slope of the foundation according to the following formula:

[0017]

[0018] Where D' is the corrected diameter of the base, D is the base diameter, α D is the diameter correction weight, d' is the depth of the corrected basis, d is the depth of the basis, α d is the depth correction weight, h' is the height of the basis after correction, h is the height of the basis, α h is the height correction weight, is the slope of the corrected foundation, The base slope, is the slope correction weight,

[0019] Furthermore, the diameter, depth, height and slope of the corrected foundation are processed and correlation analysis is performed to generate the objective functions of the cost, deformation and stability of the wind turbine foundation respectively as follows:

[0020] The cost of the wind turbine foundation and the objective function of each parameter are expressed by a polynomial:

[0021]

[0022] Among them, cost is the cost of the wind turbine foundation, a1 is the first weight coefficient of the corrected foundation diameter, a2 is the first weight coefficient of the corrected foundation depth, a3 is the first weight coefficient of the corrected foundation height, a4 is the first weight coefficient of the corrected foundation slope, a0 is the first constant term, 0 <a3<a2<a4<a1<1;

[0023] The deformation of the wind turbine foundation and the objective function of each parameter are expressed by polynomials:

[0024]

[0025] Among them, deformation is the deformation of the wind turbine foundation, b1 is the second weight coefficient of the corrected foundation diameter, b2 is the second weight coefficient of the corrected foundation depth, b3 is the second weight coefficient of the corrected foundation height, b4 is the second weight coefficient of the corrected foundation slope, b0 is the second constant term, 0 <b3<b2<b4<b1<1;

[0026] The stability of the wind turbine foundation and the objective function of each parameter are expressed by polynomials:

[0027]

[0028] Among them, stability is the stability of the wind turbine foundation, c1 is the third weight coefficient of the corrected foundation diameter, c2 is the third weight coefficient of the corrected foundation depth, c3 is the third weight coefficient of the corrected foundation height, c4 is the third weight coefficient of the corrected foundation slope, c0 is the third constant term, 0 <c3<c2<c4<c1<1。

[0029] Furthermore, the objective functions of the cost, deformation and stability of the wind turbine foundation are optimized respectively, and the process of obtaining the first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation is as follows:

[0030] Taking the minimum cost, minimum deformation and maximum stability of the wind turbine foundation as the goal, the objective functions of the cost, deformation and stability of the wind turbine foundation are optimized respectively;

[0031] Set constraints on the diameter, depth, height, and slope of the corrected foundation:

[0032] D' min ≤D'≤D' max

[0033] d' min ≤d'≤d' max

[0034] h' min ≤h'≤h' max

[0035]

[0036] Among them, D' min and D' max The minimum and maximum values ​​of the diameter of the basis, d' min and d' max The minimum and maximum depth values ​​of the basis, h' min and h' max The minimum and maximum values ​​of the base height, and The minimum and maximum values ​​of the slope diameter are taken as the basis; the above objective function is optimized by genetic algorithm, and the specific process is as follows:

[0037] Generate a set of solutions within the constraints, called the "initial population", each solution is a combination of the diameter, depth, height and slope of the corrected foundation;

[0038] For each individual, calculate its value on the three objective functions. Since we hope to meet the minimum cost, minimum deformation, and maximum stability, the fitness function is defined as follows:

[0039] Fitness 1: minimum cost;

[0040] Fitness 2: minimum deformation;

[0041] Fitness 3: Maximum stability;

[0042] According to the fitness value, a roulette wheel is used to select suitable individuals as parents, and crossover and mutation are prepared. The generated offspring individuals are merged with the current population, and fitness evaluation is performed. The best individuals are selected to form a new population. The fitness evaluation, selection, crossover and mutation operations are repeated. After multiple iterations, the Pareto optimal solution is gradually approached. An optimal solution is selected from the solutions on the Pareto frontier as the first optimized value of the diameter, depth, height and slope of the wind turbine foundation, that is, the first optimized value of the diameter, depth, height and slope of the foundation with the lowest cost. The first optimum values ​​of diameter, depth, height and slope of the foundation for minimum deformation First optimized values ​​of diameter, depth, height and slope of the foundation for maximum stability

[0043] Furthermore, the objective functions of the cost, deformation and stability of the wind turbine foundation are processed to generate a comprehensive objective function, and the comprehensive objective function of the wind turbine foundation is optimized to obtain the second optimal value of the diameter, depth, height and slope of the wind turbine foundation as follows:

[0044] The objective function of the cost of the wind turbine foundation is standardized to the range of [0,1] to obtain cost norm ;

[0045] The objective function of the deformation of the wind turbine foundation is standardized to the range of [0,1] to obtain deformation norm ;

[0046] The objective function of the stability of the wind turbine foundation is standardized to the range of [0,1] to obtain stability norm ;

[0047] The standardized objective functions are combined according to certain weights to generate a comprehensive objective function based on the following formula:

[0048] zm=ω1·cost norm +ω2·deformation norm +ω3·stability norm

[0049] Among them, zm is the comprehensive objective function, ω1 is the weight coefficient of the objective function of the standardized cost, ω2 is the weight coefficient of the objective function of the standardized deformation, ω3 is the weight coefficient of the objective function of the standardized stability, ω1<ω2<ω3, ω1+ω2+ω3=1;

[0050] Satisfy the constraints of diameter, depth, height and slope of the corrected foundation;

[0051] Set the population size to M, and each individual is a solution, that is, a combination of diameter, depth, height and slope;

[0052] Calculate the comprehensive objective function value of each individual as its fitness value, the formula is as follows:

[0053] fitness(γ)=w1·cost norm (γ)+w2·deformation norm (γ)+w3·stability norm (γ)

[0054] Among them, fitness(γ) is the fitness value of the γth individual, and γ is the index of the individual;

[0055] According to the fitness value, use the roulette wheel to select suitable individuals as parents:

[0056] Calculate the cumulative sum G of the fitness value according to the following formula:

[0057]

[0058] The probability of each individual being selected is calculated according to the following formula:

[0059]

[0060] Among them, P(γ) is the probability that the γth individual is selected as the parent;

[0061] Perform a crossover operation on the selected parent individuals to generate offspring individuals:

[0062] Randomly select a crossover point k:

[0063] k = rand(1, n)

[0064] Where n is 4, rand(1,n) is a random function that returns an integer between 1 and n;

[0065] Parent individual and Perform a single-point crossover to generate offspring individuals T and Q:

[0066]

[0067] For each offspring individual T and Q, a gene is randomly selected and slightly changed:

[0068] U j =U j +rand(-δ,δ)if rand(0,1) <p m

[0069] Among them, U j is the jth gene of the offspring individual, j is the index of the gene, rand(0, 1) is a function that generates random floating point numbers, rand(-δ, δ) is a random function that returns a value between -δ and δ, which is used to slightly change the value of the gene, p m is the mutation probability;

[0070] The generated offspring individuals are merged with the current population, fitness evaluation is performed, and the best individuals are selected to form a new population. The fitness evaluation, selection, crossover and mutation operations are repeated. After multiple iterations, the Pareto optimal solution is gradually approached. After multiple iterations, the Pareto frontier is obtained. Each point on the Pareto frontier is an optimization solution that achieves a balance between the objective functions. An optimal solution is selected from the solutions on the Pareto frontier as the second optimization value of the wind turbine foundation, that is, the second optimization value of the diameter, depth, height and slope of the foundation with the lowest cost, the smallest deformation and the greatest stability.

[0071] Further, the first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation and the second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation are calculated to obtain their respective differences, according to the following formula:

[0072] Differences in diameter, depth, height and slope of wind turbine foundation:

[0073]

[0074] Among them, ΔD is the average optimized difference of the diameter of the wind turbine foundation, Δd is the average optimized difference of the depth of the wind turbine foundation, and Δh is the average optimized difference of the height of the wind turbine foundation. is the average optimized difference of the slope of the wind turbine foundation;

[0075] Compare the respective average optimization differences with the preset difference thresholds to determine whether the optimization of diameter, depth, height and slope meets expectations, and determine whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively. The specific process is as follows:

[0076] When ΔD≤ΥZ D , the optimization of diameter meets expectations, otherwise, it does not meet expectations;

[0077] When Δd≤ΥZ d , the depth optimization meets expectations, otherwise, it does not meet expectations;

[0078] When Δh≤ΥZ h , the high degree of optimization meets expectations, otherwise, it does not meet expectations;

[0079] when The optimization of the slope meets expectations, otherwise, it does not meet expectations;

[0080] Therefore, when the optimization of the diameter, depth, height and slope are all in line with expectations, it means that the first optimization value and the second optimization value of the diameter, depth, height and slope are close. The closeness of the first optimization value and the second optimization value indicates that when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively, the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously.

[0081] To achieve the above object, the present invention also provides the following technical solutions:

[0082] A wind turbine foundation size optimization system, the system is used to execute any of the wind turbine foundation size optimization methods described above, comprising:

[0083] A data acquisition module, used to take multiple wind turbine foundations as samples to form a sample set, and collect attribute parameters and environmental load parameters of each sample in the sample set, wherein the attribute parameters include the diameter of the foundation, the depth of the foundation, the height of the foundation and the slope of the foundation, and the environmental load parameters include wind pressure, wind speed, wind direction angle, snow depth and snow load;

[0084] A correction module is used to process the wind pressure, wind speed, wind direction angle, snow depth and snow load, and perform correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation, and to correct the diameter, depth, height and slope of the wind turbine foundation by the correction coefficients to obtain the corrected diameter, depth, height and slope of the foundation;

[0085] An optimization module is used to process the diameter, depth, height and slope of the corrected foundation and perform correlation analysis to generate objective functions of the cost, deformation and stability of the wind turbine foundation, respectively, optimize the objective functions of the cost, deformation and stability of the wind turbine foundation, obtain first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation, process the objective functions of the cost, deformation and stability of the wind turbine foundation to generate a comprehensive objective function, optimize the comprehensive objective function of the wind turbine foundation, and obtain second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation;

[0086] The judgment module is used to calculate the first optimized value of the diameter, depth, height and slope of the wind turbine foundation and the second optimized value of the diameter, depth, height and slope of the wind turbine foundation respectively, obtain the respective average optimized difference values, compare the respective average optimized difference values ​​with the preset difference threshold value, judge whether the optimization of the diameter, depth, height and slope meets expectations, and judge whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively. If the conditions are met, an optimal solution is obtained. If the conditions are not met, iterative optimization is required, that is, the parameters and objective functions are readjusted, and the optimization calculation is performed again until all goals are met.

[0087] Compared with the prior art, the present invention has the following beneficial effects:

[0088] The present invention collects attribute parameters (including diameter, depth, height and slope) and environmental load parameters (including wind pressure, wind speed, wind direction angle, snow depth and snow load) of the wind turbine foundation, processes the wind pressure, wind speed, wind direction angle, snow depth and snow load, and performs correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation. The diameter, depth, height and slope of the wind turbine foundation are corrected by the correction coefficients to obtain the corrected attribute parameters. The influence of the environmental load parameters on the foundation size is considered and the correction is performed by the correction coefficients to improve the accuracy and reliability of the optimization result. The corrected foundation attribute parameters are processed and correlation analysis is performed to generate objective functions of the foundation cost, deformation and stability respectively. These objective functions are optimized to obtain the minimum cost, minimum deformation and stability respectively. The first optimization value of the basic attribute parameters of shape and maximum stability is obtained. At the same time, these objective functions are processed to generate a comprehensive objective function, and then optimized to obtain the second optimization value of the basic attribute parameters of minimum cost, minimum deformation, and maximum stability. Not only a single objective function is optimized, but also a global optimization is performed through the comprehensive objective function to ensure the balance of design in all aspects. The first optimization value and the second optimization value are calculated to obtain their respective average optimization difference, and the difference is compared with the preset threshold to determine whether the optimization meets expectations and whether the goals of minimum cost, minimum deformation, and maximum stability can be achieved at the same time. The reliability and rationality of the optimization results are further verified through difference comparison to ensure that the optimization reaches the optimal standard. Through comprehensive evaluation, it is ensured that the overall optimization effect is achieved while meeting various constraints. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0090] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0091] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0092] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0093] Example:

[0094] See also Figure 1 , the present invention provides a technical solution:

[0095] A method for optimizing the size of a wind turbine foundation, comprising the following specific steps:

[0096] S1. Taking multiple wind turbine foundations as samples to form a sample set, and collecting attribute parameters and environmental load parameters of each sample in the sample set, wherein the attribute parameters include the diameter, depth, height and slope of the foundation, and the environmental load parameters include wind pressure, wind speed, wind direction angle, snow depth and snow load;

[0097] S2. Process the wind pressure, wind speed, wind direction angle, snow depth and snow load, and perform correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation, and correct the diameter, depth, height and slope of the wind turbine foundation by the correction coefficients to obtain the corrected diameter, depth, height and slope of the foundation;

[0098] S3. Process the diameter, depth, height and slope of the corrected foundation and perform correlation analysis to generate objective functions of the cost, deformation and stability of the wind turbine foundation, respectively, optimize the objective functions of the cost, deformation and stability of the wind turbine foundation, obtain first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation, process the objective functions of the cost, deformation and stability of the wind turbine foundation to generate a comprehensive objective function, optimize the comprehensive objective function of the wind turbine foundation, and obtain second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation;

[0099] S4. Calculate the first optimized value of the diameter, depth, height and slope of the wind turbine foundation and the second optimized value of the diameter, depth, height and slope of the wind turbine foundation respectively, obtain the respective average optimized difference, compare the respective average optimized difference with the preset difference threshold, judge whether the optimization of the diameter, depth, height and slope meets expectations, and judge whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when achieving the goals of cost, deformation and stability of the wind turbine foundation respectively. If so, an optimal solution is obtained. If the conditions are not met, iterative optimization is required, that is, readjust the parameters and objective function, and perform optimization calculation again until all goals are met.

[0100] On the basis of the above embodiment, the wind pressure, wind speed, wind direction angle, snow depth and snow load are processed and correlation analysis is performed to generate correction coefficients for correcting basic attribute parameters, according to the following formula:

[0101]

[0102] Where C is the correction coefficient, W i is the wind pressure of the ith sample, P i is the wind speed of the ith sample, V i is the wind direction angle of the i-th sample, S i is the snow load of the ith sample, L i is the snow depth of the i-th sample, i is the index of the sample, and N is the number of samples.

[0103] Wind pressure W i is the force applied per unit area, the higher wind pressure W i This means that a greater force acts on the structure. i increases, the structure requires a higher safety margin to cope with this increased force, and the correction factor C is therefore designed to increase with the increase in wind pressure;

[0104] Wind speed P i The square of wind pressure W i Proportional, higher wind speed P i Means wind pressure W i The increase in wind speed P increases the load on the structure. In order to ensure that the structure is still stable under high wind speed, the correction coefficient C will increase with the wind speed P. i increases with the increase of

[0105] Wind direction V i is the angle of the wind relative to the structure, the wind direction angle V i Wind pressure W i The effect is nonlinear, ln(1+V i2 ) This term results in the wind direction angle V i Negative correlation with the correction coefficient C;

[0106] Snow load S i An increase means an increase in the weight on the structure, resulting in higher stress and potential risk. Therefore, in the model, the snow load S i An increase in will usually reduce the correction factor C;

[0107] Greater snow depth L i Means snow load S i The distribution over a larger volume reduces the pressure per unit area, which is beneficial to the structure. Therefore, it is reflected in the model as an increase in the correction coefficient C. From a design perspective, a larger snow depth L i It provides a certain cushioning effect, allowing the structure to better adapt to and distribute the load.

[0108] In summary, the wind pressure W i , wind speed P i 、Snow depth L i The average is positively correlated with the correction coefficient C, and the wind direction angle V i , Snow load S i They are negatively correlated with the correction coefficient C.

[0109] On the basis of the above embodiment, the diameter, depth, height and slope of the wind turbine foundation are corrected by the correction coefficient to obtain the corrected diameter, depth, height and slope of the foundation, according to the following formula:

[0110]

[0111] Where D' is the corrected diameter of the base, D is the base diameter, α D is the diameter correction weight, d' is the depth of the corrected basis, d is the depth of the basis, α d is the depth correction weight, h' is the height of the basis after correction, h is the height of the basis, α h is the height correction weight, is the slope of the corrected foundation, The base slope, is the slope correction weight,

[0112] The larger the diameter D of the foundation, the larger the area in contact with the ground, the higher the overall stability of the foundation, and the stronger the ability to resist overturning and sliding. A larger diameter D can disperse the weight and wind load of the wind turbine, reduce the stress per unit area, and improve the bearing capacity of the foundation. For the foundation of a wind turbine, stability is crucial because wind turbines are often affected by the combined effects of wind force and deadweight. Diameter D directly affects the overall safety and service life of the foundation, so it has the greatest weight. Influence of friction on soil-structure interface, suitable slope It can improve the foundation's shear resistance. Reasonable slope design can effectively control the overall deformation of the foundation and reduce excessive settlement and tilt. It has an important influence on stability and shear resistance, but due to the usual design of slope The range of variation is small, and its influence is relatively minor relative to the diameter D. The appropriate slope The design can still significantly improve the stability of the foundation, so its weight is second only to the diameter D; a deeper foundation can more effectively resist the load of the superstructure and reduce the local instability of the foundation. A deeply buried foundation helps to reduce the deformation of the foundation and provide better support. The depth d has a significant effect on deformation and stability, but its optimization space and influence are slightly weaker than the slope d. The depth correction weight is important but second only to the slope; the foundation height h directly affects the installation height of the wind turbine, thereby affecting the wind energy capture efficiency. Changes in the foundation height h have little direct and short-term impact on the foundation, and have limited impact on the cost and overall stability. Compared with other parameters, the foundation height h has little direct impact on the optimization target, and mainly affects the wind energy capture efficiency rather than the stability and bearing capacity of the foundation. The height correction weight is the least important in the optimization target.

[0113] On the basis of the above embodiment, the diameter, depth, height and slope of the corrected foundation are processed and correlation analysis is performed to generate the objective functions of the cost, deformation and stability of the wind turbine foundation respectively as follows:

[0114] The cost of the wind turbine foundation and the objective function of each parameter are expressed by a polynomial:

[0115]

[0116] Among them, cost is the cost of the wind turbine foundation, a1 is the first weight coefficient of the corrected foundation diameter, a2 is the first weight coefficient of the corrected foundation depth, a3 is the first weight coefficient of the corrected foundation height, a4 is the first weight coefficient of the corrected foundation slope, a0 is the first constant term, 0 <a3<a2<a4<a1<1。

[0117] The deformation of the wind turbine foundation and the objective function of each parameter are expressed by polynomials:

[0118]

[0119] Among them, deformation is the deformation of the wind turbine foundation, b1 is the second weight coefficient of the corrected foundation diameter, b2 is the second weight coefficient of the corrected foundation depth, b3 is the second weight coefficient of the corrected foundation height, b4 is the second weight coefficient of the corrected foundation slope, b0 is the second constant term, 0 <b3<b2<b4<b1<1。

[0120] The stability of the wind turbine foundation and the objective function of each parameter are expressed by polynomials:

[0121]

[0122] Among them, stability is the stability of the wind turbine foundation, c1 is the third weight coefficient of the corrected foundation diameter, c2 is the third weight coefficient of the corrected foundation depth, c3 is the third weight coefficient of the corrected foundation height, c4 is the third weight coefficient of the corrected foundation slope, c0 is the third constant term, 0 <c3<c2<c4<c1<1。

[0123] On the basis of the above embodiment, the objective functions of the cost, deformation and stability of the wind turbine foundation are optimized respectively, and the process of obtaining the first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation is as follows:

[0124] Taking the minimum cost, minimum deformation and maximum stability of the wind turbine foundation as the goal, the objective functions of the cost, deformation and stability of the wind turbine foundation are optimized respectively;

[0125] Set constraints on the diameter, depth, height, and slope of the corrected foundation:

[0126] D' min ≤D'≤D' max

[0127] d' min ≤d'≤d' max

[0128] h' min ≤h'≤h' max

[0129]

[0130] Among them, D' min and D' max The minimum and maximum values ​​of the diameter of the basis, d' min and d' max The minimum and maximum depth values ​​of the basis, h'min and h' max The minimum and maximum values ​​of the base height, and The minimum and maximum values ​​of the slope diameter are taken as the basis; the above objective function is optimized by genetic algorithm, and the specific process is as follows:

[0131] Generate a set of possible solutions within the constraints, called the "initial population", each solution is a combination of the diameter, depth, height and slope of the corrected foundation;

[0132] For each individual, calculate its value on the three objective functions (cost, deformation and stability). Since we hope to meet the minimum cost, minimum deformation and maximum stability, the fitness function is defined as follows:

[0133] Fitness 1: minimum cost;

[0134] Fitness 2: minimum deformation;

[0135] Fitness 3: Maximum stability;

[0136] According to the fitness value, a roulette wheel is used to select suitable individuals as parents, and crossover and mutation are prepared. The generated offspring individuals are merged with the current population, and fitness evaluation is performed. The best individuals are selected to form a new population. The fitness evaluation, selection, crossover and mutation operations are repeated. After multiple iterations, the Pareto optimal solution is gradually approached. An optimal solution is selected from the solutions on the Pareto frontier as the first optimized value of the diameter, depth, height and slope of the wind turbine foundation, that is, the first optimized value of the diameter, depth, height and slope of the foundation with the lowest cost. The first optimum values ​​of diameter, depth, height and slope of the foundation for minimum deformation First optimized values ​​of diameter, depth, height and slope of the foundation for maximum stability

[0137] On the basis of the above embodiment, the objective functions of the cost, deformation and stability of the wind turbine foundation are processed to generate a comprehensive objective function, and the comprehensive objective function of the wind turbine foundation is optimized to obtain the second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation as follows:

[0138] The objective function of the cost of the wind turbine foundation is standardized to the range of [0,1] to obtain cost norm ;

[0139] The objective function of the deformation of the wind turbine foundation is standardized to the range of [0,1] to obtain deformation norm ;

[0140] The objective function of the stability of the wind turbine foundation is standardized to the range of [0,1] to obtain stability norm ;

[0141] The standardized objective functions are combined according to certain weights to generate a comprehensive objective function based on the following formula:

[0142] zm=ω1·cost norm +ω2·deformation norm +ω3·stability norm

[0143] Among them, zm is the comprehensive objective function, ω1 is the weight coefficient of the objective function of the standardized cost, ω2 is the weight coefficient of the objective function of the standardized deformation, ω3 is the weight coefficient of the objective function of the standardized stability, ω1<ω2<ω3, ω1+ω2+ω3=1;

[0144] Stability is usually the most important factor in the design of wind turbine foundations, because an unstable foundation may cause the collapse or failure of the entire wind turbine. Therefore, the weight coefficient ω3 of the stability objective function is the largest; deformation has a significant impact on the long-term performance and service life of the foundation. Excessive deformation will affect the normal operation and maintenance of the wind turbine. The weight coefficient ω2 of the deformation objective function should be second to stability; although economic cost is also an important factor to consider, cost optimization is usually relatively secondary under the premise of ensuring safety and performance. Therefore, the weight coefficient ω1 of the cost objective function is the smallest.

[0145] Satisfy the constraints of diameter, depth, height and slope of the corrected foundation;

[0146] Set the population size to M, and each individual is a solution, that is, a combination of diameter, depth, height and slope;

[0147] Calculate the comprehensive objective function value of each individual as its fitness value, the formula is as follows:

[0148] fitness(γ)=w1·cost norm (γ)+w2·deformation norm (γ)+w3·stability norm (γ)

[0149] Among them, fitness(γ) is the fitness value of the γth individual, and γ is the index of the individual;

[0150] According to the fitness value, use the roulette wheel to select suitable individuals as parents:

[0151] Calculate the cumulative sum G of the fitness value according to the following formula:

[0152]

[0153] The probability of each individual being selected is calculated according to the following formula:

[0154]

[0155] Among them, P(γ) is the probability that the γth individual is selected as the parent,

[0156] Perform a crossover operation on the selected parent individuals to generate offspring individuals:

[0157] Randomly select a crossover point k:

[0158] k = rand(1, n)

[0159] Where n is 4, rand(1,n) is a random function that returns an integer between 1 and n;

[0160] Parent individual and Perform a single-point crossover to generate offspring individuals T and Q:

[0161]

[0162] For each offspring individual T and Q, a gene is randomly selected and slightly changed:

[0163] U j =U j +rand(-δ,δ)if rand(0,1) <p m

[0164] Among them, U j is the jth gene of the offspring individual, j is the index of the gene, rand(0, 1) is a function that generates random floating point numbers, rand(-δ, δ) is a random function that returns a value between -δ and δ, which is used to slightly change the value of the gene, p m is the mutation probability;

[0165] The generated offspring individuals are merged with the current population, fitness evaluation is performed, and the best individuals are selected to form a new population. The fitness evaluation, selection, crossover and mutation operations are repeated. After multiple iterations, the Pareto optimal solution is gradually approached. After multiple iterations, the Pareto frontier is obtained. Each point on the Pareto frontier is an optimization solution that achieves a balance between the objective functions. An optimal solution is selected from the solutions on the Pareto frontier as the second optimization value of the wind turbine foundation, that is, the second optimization value of the diameter, depth, height and slope of the foundation with the lowest cost, the smallest deformation and the greatest stability.

[0166] On the basis of the above embodiment, the first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation and the second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation are calculated respectively to obtain their respective average optimized differences, according to the following formula:

[0167] Average optimized differences in diameter, depth, height and slope of wind turbine foundations:

[0168]

[0169] Among them, ΔD is the average optimized difference of the diameter of the wind turbine foundation, Δd is the average optimized difference of the depth of the wind turbine foundation, and Δh is the average optimized difference of the height of the wind turbine foundation. is the average optimized difference of the slope of the wind turbine foundation.

[0170] Compare the respective optimized differences with the preset difference thresholds to determine whether the optimization of diameter, depth, height and slope meets expectations, and determine whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively. The specific process is as follows:

[0171] When ΔD≤ΥZ D , the optimization of diameter meets expectations, otherwise, it does not meet expectations;

[0172] When Δd≤ΥZ d , the depth optimization meets expectations, otherwise, it does not meet expectations;

[0173] When Δh≤ΥZ h , the high degree of optimization meets expectations, otherwise, it does not meet expectations;

[0174] when The optimization of the slope is as expected, otherwise, it is not as expected.

[0175] Therefore, when the optimization of the diameter, depth, height and slope are all in line with expectations, it means that the first optimization value and the second optimization value of the diameter, depth, height and slope are close. The closeness of the first optimization value and the second optimization value indicates that when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively, the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can also be achieved simultaneously.

[0176] See also Figure 2 , the present invention provides a technical solution:

[0177] A wind turbine foundation size optimization system, the system is used to execute any of the wind turbine foundation size optimization methods described above, comprising:

[0178] A data acquisition module, used to take multiple wind turbine foundations as samples to form a sample set, and collect attribute parameters and environmental load parameters of each sample in the sample set, wherein the attribute parameters include the diameter of the foundation, the depth of the foundation, the height of the foundation and the slope of the foundation, and the environmental load parameters include wind pressure, wind speed, wind direction angle, snow depth and snow load;

[0179] A correction module is used to process the wind pressure, wind speed, wind direction angle, snow depth and snow load, and perform correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation, and to correct the diameter, depth, height and slope of the wind turbine foundation by the correction coefficients to obtain the corrected diameter, depth, height and slope of the foundation;

[0180] An optimization module is used to process the diameter, depth, height and slope of the corrected foundation and perform correlation analysis to generate objective functions of the cost, deformation and stability of the wind turbine foundation, respectively, optimize the objective functions of the cost, deformation and stability of the wind turbine foundation, obtain first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation, process the objective functions of the cost, deformation and stability of the wind turbine foundation to generate a comprehensive objective function, optimize the comprehensive objective function of the wind turbine foundation, and obtain second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation;

[0181] The judgment module is used to calculate the first optimized value of the diameter, depth, height and slope of the wind turbine foundation and the second optimized value of the diameter, depth, height and slope of the wind turbine foundation respectively, obtain the respective average optimized difference values, compare the respective average optimized difference values ​​with the preset difference threshold value, judge whether the optimization of the diameter, depth, height and slope meets expectations, and judge whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively. If the conditions are met, an optimal solution is obtained. If the conditions are not met, iterative optimization is required, that is, the parameters and objective functions are readjusted, and the optimization calculation is performed again until all goals are met.

[0182] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0183] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0184] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for optimizing the size of a wind turbine foundation, characterized in that: The specific steps include: S1. Taking multiple wind turbine foundations as samples to form a sample set, and collecting attribute parameters and environmental load parameters of each sample in the sample set, wherein the attribute parameters include the diameter, depth, height and slope of the foundation, and the environmental load parameters include wind pressure, wind speed, wind direction angle, snow depth and snow load; S2. Process the wind pressure, wind speed, wind direction angle, snow depth and snow load, and perform correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation, and correct the diameter, depth, height and slope of the wind turbine foundation by the correction coefficients to obtain the corrected diameter, depth, height and slope of the foundation; S3. Process the diameter, depth, height and slope of the corrected foundation and perform correlation analysis to generate objective functions of the cost, deformation and stability of the wind turbine foundation, respectively, optimize the objective functions of the cost, deformation and stability of the wind turbine foundation, obtain first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation, process the objective functions of the cost, deformation and stability of the wind turbine foundation to generate a comprehensive objective function, optimize the comprehensive objective function of the wind turbine foundation, and obtain second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation; S4. Calculate the first optimized value of the diameter, depth, height and slope of the wind turbine foundation and the second optimized value of the diameter, depth, height and slope of the wind turbine foundation respectively, obtain the respective average optimized difference, compare the respective average optimized difference with the preset difference threshold, judge whether the optimization of the diameter, depth, height and slope meets expectations, and judge whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when achieving the goals of cost, deformation and stability of the wind turbine foundation respectively. If so, an optimal solution is obtained. If the conditions are not met, iterative optimization is required, that is, readjust the parameters and objective function, and perform optimization calculation again until all goals are met.

2. The method for optimizing the foundation size of a wind turbine generator set according to claim 1, characterized in that: The wind pressure, wind speed, wind direction angle, snow depth and snow load are processed and correlated to generate correction coefficients for basic attribute parameters. The formula is as follows: Where C is the correction coefficient, W i is the wind pressure of the ith sample, P i is the wind speed of the ith sample, V i is the wind direction angle of the i-th sample, S i is the snow load of the ith sample, L i is the snow depth of the i-th sample, i is the index of the sample, and N is the number of samples.

3. The method for optimizing the foundation size of a wind turbine generator set according to claim 2, characterized in that: The diameter, depth, height and slope of the wind turbine foundation are corrected by the correction coefficient to obtain the corrected diameter, depth, height and slope of the foundation according to the following formula: Where D' is the corrected diameter of the base, D is the base diameter, and α D is the diameter correction weight, d' is the depth of the corrected basis, d is the depth of the basis, α d is the depth correction weight, h' is the height of the basis after correction, h is the height of the basis, α h is the height correction weight, is the slope of the corrected foundation, The base slope, is the slope correction weight, 4. The method for optimizing the foundation size of a wind turbine generator set according to claim 3, characterized in that: The process of processing the diameter, depth, height and slope of the corrected foundation and performing correlation analysis to generate the objective functions of the cost, deformation and stability of the wind turbine foundation is as follows: The cost of the wind turbine foundation and the objective function of each parameter are expressed by a polynomial: Among them, cost is the cost of the wind turbine foundation, a1 is the first weight coefficient of the corrected foundation diameter, a2 is the first weight coefficient of the corrected foundation depth, a3 is the first weight coefficient of the corrected foundation height, a4 is the first weight coefficient of the corrected foundation slope, a0 is the first constant term, 0 <a3<a2<a4<a1<1; The deformation of the wind turbine foundation and the objective function of each parameter are expressed by polynomials: Among them, deformation is the deformation of the wind turbine foundation, b1 is the second weight coefficient of the corrected foundation diameter, b2 is the second weight coefficient of the corrected foundation depth, b3 is the second weight coefficient of the corrected foundation height, b4 is the second weight coefficient of the corrected foundation slope, b0 is the second constant term, 0 <b3<b2<b4<b1<1; The stability of the wind turbine foundation and the objective function of each parameter are expressed by polynomials: Among them, stability is the stability of the wind turbine foundation, c1 is the third weight coefficient of the corrected foundation diameter, c2 is the third weight coefficient of the corrected foundation depth, c3 is the third weight coefficient of the corrected foundation height, c4 is the third weight coefficient of the corrected foundation slope, c0 is the third constant term, 0 <c3<c2<c4<c1<1。 5. The method for optimizing the foundation size of a wind turbine generator set according to claim 4, characterized in that: The objective functions of the cost, deformation and stability of the wind turbine foundation are optimized respectively, and the process of obtaining the first optimization value of the diameter, depth, height and slope of the wind turbine foundation is as follows: Taking the minimum cost, minimum deformation and maximum stability of the wind turbine foundation as the goal, the objective functions of the cost, deformation and stability of the wind turbine foundation are optimized respectively; Set constraints on the diameter, depth, height, and slope of the corrected foundation: D’ min ≤D’≤D’ max d’ min ≤d’≤d’ max h’ min ≤h’≤h’ max Among them, D' min and D' max The minimum and maximum values ​​of the diameter of the basis, d' min and d' max The minimum and maximum depth values ​​of the basis, h' min and h' max The minimum and maximum values ​​of the base height, and The minimum and maximum values ​​of the slope diameter as the basis; The above objective function is optimized by genetic algorithm. The specific process is as follows: Generate a set of solutions within the constraints, called the "initial population", each solution is a combination of the diameter, depth, height and slope of the corrected foundation; For each individual, calculate its value on the three objective functions. Since we hope to meet the minimum cost, minimum deformation, and maximum stability, the fitness function is defined as follows: Fitness 1: minimum cost; Fitness 2: minimum deformation; Fitness 3: Maximum stability; According to the fitness value, a suitable individual is selected as the parent using a roulette wheel, and crossover and mutation are prepared. The generated offspring individuals are merged with the current population, and fitness evaluation is performed. The best individuals are selected to form a new population. The fitness evaluation, selection, crossover and mutation operations are repeated. After multiple iterations, the Pareto optimal solution is gradually approached. An optimal solution is selected from the solutions on the Pareto frontier as the first optimized value of the diameter, depth, height and slope of the wind turbine foundation, that is, the first optimized value of the diameter, depth, height and slope of the foundation with the lowest cost. The first optimum values ​​of diameter, depth, height and slope of the foundation for minimum deformation First optimized values ​​of diameter, depth, height and slope of the foundation for maximum stability 6. The method for optimizing the foundation size of a wind turbine generator set according to claim 5, characterized in that: The objective functions of the cost, deformation and stability of the wind turbine foundation are processed to generate a comprehensive objective function, and the comprehensive objective function of the wind turbine foundation is optimized to obtain the second optimal value of the diameter, depth, height and slope of the wind turbine foundation as follows: The objective function of the cost of the wind turbine foundation is standardized to the range of [0,1] to obtain cost norm ; The objective function of the deformation of the wind turbine foundation is standardized to the range of [0,1] to obtain deformation norm ; The objective function of the stability of the wind turbine foundation is standardized to the range of [0,1] to obtain stability norm ; The standardized objective functions are combined according to certain weights to generate a comprehensive objective function based on the following formula: zm=ω1·cost norm +ω2·deformation norm +ω3·stability norm Among them, zm is the comprehensive objective function, ω1 is the weight coefficient of the objective function of the standardized cost, ω2 is the weight coefficient of the objective function of the standardized deformation, ω3 is the weight coefficient of the objective function of the standardized stability, ω1<ω2<ω3, ω1+ω2+ω3=1; Satisfy the constraints of diameter, depth, height and slope of the corrected foundation; Set the population size to M, and each individual is a solution, that is, a combination of diameter, depth, height and slope; Calculate the comprehensive objective function value of each individual as its fitness value, the formula is as follows: fitness(γ)=w1·cost norm (c)+w2·deformation norm (c)+w3·stability norm (c) Among them, fitness(γ) is the fitness value of the γth individual, and γ is the index of the individual; According to the fitness value, use the roulette wheel to select suitable individuals as parents: Calculate the cumulative sum G of the fitness value according to the following formula: The probability of each individual being selected is calculated according to the following formula: Among them, P(γ) is the probability that the γth individual is selected as the parent; Perform a crossover operation on the selected parent individuals to generate offspring individuals: Randomly select a crossover point k: k = rand(1, n) Where n is 4, rand(1,n) is a random function that returns an integer between 1 and n; Parent individual and Perform a single-point crossover to generate offspring individuals T and Q: For each offspring individual T and Q, a gene is randomly selected and slightly changed: U j =U j +rand(-δ,δ)if rand(0,1)<p m Among them, U j is the jth gene of the offspring individual, j is the index of the gene, rand(0, 1) is a function that generates random floating point numbers, rand(-δ, δ) is a random function that returns a value between -δ and δ, which is used to slightly change the value of the gene, p m is the mutation probability; The generated offspring individuals are merged with the current population, and fitness evaluation is performed. The best individuals are selected to form a new population. The fitness evaluation, selection, crossover and mutation operations are repeated. After multiple iterations, the Pareto optimal solution is gradually approached. After multiple iterations, the Pareto frontier is obtained. Each point on the Pareto frontier is an optimal solution that achieves a balance between the objective functions. An optimal solution is selected from the solutions on the Pareto frontier as the second optimal value of the wind turbine foundation, that is, the second optimal value of the diameter, depth, height and slope of the foundation with the lowest cost, the smallest deformation and the greatest stability.

7. The method for optimizing the foundation size of a wind turbine generator set according to claim 6, characterized in that: The first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation and the second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation are calculated respectively to obtain their respective average optimized differences, according to the following formula: Average optimized differences in diameter, depth, height and slope of wind turbine foundations: Wherein, ΔD is the average optimized difference of the diameter of the wind turbine foundation, Δd is the average optimized difference of the depth of the wind turbine foundation, Δh is the average optimized difference of the height of the wind turbine foundation, and Δζ is the average optimized difference of the slope of the wind turbine foundation; Compare the respective average optimization differences with the preset difference thresholds to determine whether the optimization of diameter, depth, height and slope meets expectations, and determine whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively. The specific process is as follows: When ΔD≤ΥZ D , the optimization of diameter meets expectations, otherwise, it does not meet expectations; When Δd≤ΥZ d , the depth optimization meets expectations, otherwise, it does not meet expectations; When Δh≤ΥZ h , the high degree of optimization meets expectations, otherwise, it does not meet expectations; When Δζ≤ΥZ ζ , the optimization of the slope meets expectations, otherwise, it does not meet expectations; Therefore, when the optimization of the diameter, depth, height and slope are all in line with expectations, it means that the first optimization value and the second optimization value of the diameter, depth, height and slope are close. The closeness of the first optimization value and the second optimization value indicates that when the goals of the cost, deformation and stability of the wind turbine foundation are achieved respectively, the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously.

8. A wind turbine foundation size optimization system, the system being used to execute a wind turbine foundation size optimization method according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, used to take multiple wind turbine foundations as samples to form a sample set, and collect attribute parameters and environmental load parameters of each sample in the sample set, wherein the attribute parameters include the diameter of the foundation, the depth of the foundation, the height of the foundation and the slope of the foundation, and the environmental load parameters include wind pressure, wind speed, wind direction angle, snow depth and snow load; A correction module is used to process the wind pressure, wind speed, wind direction angle, snow depth and snow load, and perform correlation analysis to generate correction coefficients for correcting the attribute parameters of the wind turbine foundation, and to correct the diameter, depth, height and slope of the wind turbine foundation by the correction coefficients to obtain the corrected diameter, depth, height and slope of the foundation; An optimization module is used to process the diameter, depth, height and slope of the corrected foundation and perform correlation analysis to generate objective functions of the cost, deformation and stability of the wind turbine foundation, respectively, optimize the objective functions of the cost, deformation and stability of the wind turbine foundation, obtain first optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation, process the objective functions of the cost, deformation and stability of the wind turbine foundation to generate a comprehensive objective function, optimize the comprehensive objective function of the wind turbine foundation, and obtain second optimized values ​​of the diameter, depth, height and slope of the wind turbine foundation; The judgment module is used to calculate the first optimized value of the diameter, depth, height and slope of the wind turbine foundation and the second optimized value of the diameter, depth, height and slope of the wind turbine foundation respectively, obtain the respective average optimized difference values, compare the respective average optimized difference values ​​with the preset difference threshold value, judge whether the optimization of the diameter, depth, height and slope meets expectations, and judge whether the goals of minimum cost, minimum deformation and maximum stability of the wind turbine foundation can be achieved simultaneously when the goals of cost, deformation and stability of the wind turbine foundation are achieved respectively. If the conditions are met, an optimal solution is obtained. If the conditions are not met, iterative optimization is required, that is, the parameters and objective functions are readjusted, and the optimization calculation is performed again until all goals are met.

Images