A wind farm wind turbine foundation intelligent design method and system

Abstract

The application provides a wind turbine foundation intelligent design method and system, and relates to the technical field of wind turbine foundation design, and the specific steps include: obtaining the size, geological conditions, soil mechanical parameters and environmental parameters of previous wind turbine foundations, and evaluating through expert scoring; generating multiple initial combinations of wind turbine foundation sizes according to previous data and a scoring model; iteratively optimizing the initial combinations by using a genetic algorithm to obtain optimal wind turbine foundation design sizes; calculating the average stability coefficient of changes according to the historical changes of the geological conditions, soil mechanical parameters and environmental parameters of the site where the wind turbine foundation is to be built; and correcting the optimal sizes using the average stability coefficient to adapt to the requirements of the actual environment. The application realizes quantitative evaluation of site conditions and environmental parameters, accurately reflects the influence of the site conditions and environmental parameters on the performance of the wind turbine foundation, intelligently adjusts the design parameters according to the requirements of the actual environment, and makes the design results more suitable for the actual environment.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of fan foundation design, in particular to an intelligent design method and system for a fan foundation of a wind farm. BACKGROUND

[0002] The intelligent design method and system for a fan foundation of a wind farm refer to using artificial intelligence, big data analysis, machine learning and other technologies to intelligently and automatically design a fan foundation. Such a method and system can help engineers and designers more quickly and accurately design a fan foundation, improving design efficiency and quality.

[0003] In the prior art, the application number CN115470650A discloses an automatic design method and device for a fan foundation of a wind farm. For a shallow buried foundation, the method uses a multiple iteration calculation method to calculate the fan foundation design result, and finally calculates the fan foundation design result and the engineering quantity. For a deep foundation, the method uses automatic matching of a preset foundation engineering quantity, and then according to the load range, a design result is obtained according to the geological conditions, and finally the fan foundation design result and the engineering quantity are calculated. The method has strong operability, improves the degree of automation of the design of the fan foundation of the wind farm, greatly reduces the process of the design of the fan foundation under the requirement of meeting the reliability of the bearing capacity of the fan foundation, has strong engineering applicability, and is suitable for the automatic design of the fan foundation of the wind farm at home and abroad, fills the blank in the field of automatic design and engineering quantity calculation of the fan foundation of the wind farm.

[0004] However, there are still the following deficiencies: as can be known from the above statement, the prior art does not specifically quantify the influence of site conditions and environmental parameters on the fan foundation, but the performance of the fan foundation under different geological conditions and environmental influences is significantly different, and the scheme fails to intelligently adjust the design parameters according to the actual situation, so that the design result cannot meet the requirements of the actual environment, a static design standard is used, and the comprehensive application of real-time monitoring data and historical data is not considered, thereby limiting the optimized design and stability evaluation of the fan foundation.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide an intelligent design method and system for a fan foundation of a wind farm to solve the problems raised in the background.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0008] An intelligent design method for a fan foundation of a wind farm, comprising the following specific steps:

[0009] S1. Obtain the size of the previous fan foundation and the geological conditions and soil mechanical parameters of the construction site thereof, and score them by an expert group, take the size and the geological conditions and soil mechanical parameters of the construction site thereof as input, take the score as label, train the scoring model, obtain the model after training is completed, obtain the expression of the fan foundation design score;

[0010] S2. Obtain the geological conditions and soil mechanical parameters of the construction site of the current to-be-built fan foundation, and generate multiple initial combinations of the size of the fan foundation according to the size of the previous fan foundation, splice the initial combination with the geological conditions and soil mechanical parameters to form an initial population;

[0011] S3. According to the expression of the fan foundation design score, calculate the fan foundation design score of each individual in the initial population, take the maximization of the fan foundation design score as the optimization goal, use genetic algorithm to iteratively optimize the initial population, generate the optimal individual, and extract the optimal size of the wind power foundation;

[0012] S4. According to the historical changes of the geological conditions, soil mechanical parameters and environmental parameters of the current to-be-built fan foundation construction site, calculate the stability of the changes, take the stability as the correction number, and correct the optimal size.

[0013] Further, the diameter of the fan foundation, the height of the fan foundation, and the ground elevation, the underground water level, the soil density, the porosity, the shear strength, and the compressive strength are collected to calculate the geological score of the fan foundation. The obtained fan foundation design score expression is as follows:

[0014]

[0015] Wherein, PF is the geological score of the fan foundation, D is the diameter of the fan foundation, H is the height of the fan foundation, E is the ground elevation, W is the underground water level, M is the soil density, K is the porosity, J is the shear strength, Q is the compressive strength, α is the weight coefficient of the diameter of the fan foundation, β is the weight coefficient of the height of the fan foundation, γ is the weight coefficient of the ground elevation, κ is the weight coefficient of the underground water level, λ is the weight coefficient of the soil density, μ is the weight coefficient of the porosity, ω is the weight coefficient of the shear strength, and is the weight coefficient of the compressive strength,

[0016] Further, the scoring model adopts a convolutional neural network model, which is composed of a multilayer perceptron-based deep neural network, including an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, each of the first, second and third hidden layers has at least two neurons, and each adopts ReLU as an activation function.

[0017] Further, the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site are obtained, and a plurality of initial combinations of the size of the wind turbine foundation are generated according to the size of the previous wind turbine foundation, and the specific process is as follows:

[0018] The geological conditions and soil mechanical parameters of the current wind turbine foundation construction site are collected, including ground elevation E, underground water level W, soil density M, porosity K, shear strength J, and compressive strength Q, the jth initial combination is labeled as Bj, j is the index of the initial combination, and j [1, m], m is the number of initial combinations, and Bj = {Dj, Hj}, Dj and Hj represent the diameter and height in the jth initial combination, respectively, and the initial population formed by splicing is labeled as A, and the initial population A = {A1, A2, …, Aj, …, Am}, Aj is the jth individual in the initial population, and Aj = {E,, W,, M,, K,, J,, Q,, Dj, Hj}.

[0019] Further, the initial population A is iteratively optimized, that is, the individuals in the initial population A are selected, crossed and mutated, specifically, the individuals with the top design score values of the wind turbine foundation are selected as the parents, the genes of the parent individuals are exchanged and combined through the crossing operation, and new individuals are generated, and after the genes of the diameter and height in the newly generated individuals are mutated, the selection, crossing and mutation operations are repeated until the stopping condition is reached.

[0020] After the initial population A is iteratively optimized, the optimal individual is labeled as Aj1 = {E,, W,, M,, K,, J,, Q,, Dj1, Hj1}, and the optimal size of the wind turbine foundation is diameter Dj1 and height Hj1.

[0021] Further, according to the historical change of the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site, the stability coefficient of the change is obtained, and the specific process is as follows:

[0022] The geological conditions and soil mechanical parameters of the wind turbine foundation construction site at T collection time points in the historical period are collected, that is,

[0023] E, = {E, (1), E, (2), …, E, (t), …, E, (T)}

[0024] W, = {W, (1), W, (2), …, W, (t), …, W, (T)}

[0025] M, = {M, (1), M, (2), …, M, (t), …, M, (T)}

[0026] K, = {K, (1), K, (2), …, K, (t), …, K, (T)}

[0027] J, = {J, (1), J, (2), …, J, (t), …, J, (T)}

[0028] Q, = {Q, (1), Q, (2), …, Q, (t), …, Q, (T)}

[0029] Wherein, E, (t) is the ground elevation of the to-be-built wind turbine foundation construction site at the tth collection moment, W, (t) is the underground water level of the to-be-built wind turbine foundation construction site at the tth collection moment, M, (t) is the soil density of the to-be-built wind turbine foundation construction site at the tth collection moment, K, (t) is the porosity of the to-be-built wind turbine foundation construction site at the tth collection moment, J, (t) is the shear strength of the to-be-built wind turbine foundation construction site at the tth collection moment, and Q, (t) is the compressive strength of the to-be-built wind turbine foundation construction site at the tth collection moment.

[0030] Further, the stability coefficients of the parameters and the average stability coefficient are obtained according to the following formula:

[0031]

[0032] PS = (ES + WS + MS + KS + JS + QS) / 6

[0033] Wherein, ES is the stability coefficient of the ground elevation of the to-be-built wind turbine foundation construction site, WS is the stability coefficient of the underground water level of the to-be-built wind turbine foundation construction site, MS is the stability coefficient of the soil density of the to-be-built wind turbine foundation construction site, KS is the stability coefficient of the porosity of the to-be-built wind turbine foundation construction site, JS is the stability coefficient of the shear strength of the to-be-built wind turbine foundation construction site, QS is the stability coefficient of the compressive strength of the to-be-built wind turbine foundation construction site, and PS is the average stability coefficient.

[0034] Further, the average stability coefficient PS is taken as a correction coefficient to correct the optimal size according to the following formula:

[0035] D, j1 = Dj1 x PS

[0036] H, j1 = Hj1 x PS

[0037] Wherein, D, j1 is the corrected diameter of the wind turbine foundation, and H, j1 is the corrected height of the wind turbine foundation.

[0038] The application discloses a wind turbine foundation intelligent design system, which is used for executing the wind turbine foundation intelligent design method.

[0039] The scoring acquisition module is used for acquiring the size of the previous wind turbine foundation and the geological condition and soil mechanical parameter of the construction site of the previous wind turbine foundation, and scoring the size of the previous wind turbine foundation and the geological condition and soil mechanical parameter of the construction site of the previous wind turbine foundation by an expert group, wherein the size and the geological condition and soil mechanical parameter of the construction site are taken as inputs, the score is taken as a label, the scoring model is trained, and the model after training is obtained, and the expression of the geological score of the wind turbine foundation is acquired.

[0040] The data processing module is used for acquiring the geological condition and soil mechanical parameter of the current wind turbine foundation construction site, and generating a plurality of initial combinations of the size of the wind turbine foundation according to the size of the previous wind turbine foundation, wherein the initial combination is spliced with the geological condition and soil mechanical parameter to form an initial population.

[0041] The size optimization module is used for calculating the wind turbine foundation design score of each individual in the initial population according to the expression of the wind turbine foundation design score, taking the maximization of the wind turbine foundation design score as an optimization target, and iteratively optimizing the initial population by using a genetic algorithm to generate an optimal individual, and extracting the optimal size of the wind turbine foundation.

[0042] The correction module is used for calculating the average stability coefficient of the historical change of the geological condition and soil mechanical parameter of the current wind turbine foundation construction site, taking the average stability coefficient as a correction coefficient, and correcting the optimal size.

[0043] Compared with the prior art, the application has the following beneficial effects:

[0044] The application acquires the size of the previous wind turbine foundation and the geological condition, soil mechanical parameter and environmental parameter of the construction site of the previous wind turbine foundation, scores the parameters by an expert group, takes the parameters as inputs for training, and obtains a scoring model, so that the quantitative evaluation of the site condition and environmental parameter can be realized, and the influence of the site condition and environmental parameter on the performance of the wind turbine foundation can be accurately reflected.

[0045] The initial population is iteratively optimized by using a genetic algorithm to generate an optimal combination, the average stability coefficient of the historical change of the geological condition, soil mechanical parameter and environmental parameter of the current wind turbine foundation construction site is calculated, the average stability coefficient is taken as a correction number, the optimal size is corrected, and the design parameter can be intelligently adjusted according to the actual environmental requirement, so that the design result is more suitable for the actual environment.

[0046] By acquiring the geological conditions, soil mechanical parameters and environmental parameters of the construction site of the current to-be-built wind turbine foundation, and combining historical data to train and optimize the scoring model, the comprehensive application of real-time monitoring data and historical data can be fully utilized, and the accuracy of the optimization design and stability evaluation of the wind turbine foundation can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 It is a whole method flowchart of the present application;

[0048] Figure 2 It is a module composition block diagram of the present application. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0050] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the usual meaning understood by those skilled in the art to which the present application belongs. The "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationship, when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0051] Embodiment:

[0052] Please refer to Figure 1 The present application provides a technical solution:

[0053] A wind turbine foundation intelligent design method for a wind farm, the specific steps comprising:

[0054] S1. Acquire the size of the previous wind turbine foundation and the geological conditions and soil mechanical parameters of its construction site, and score it by an expert group, use the size and the geological conditions and soil mechanical parameters of its construction site as input, and use the score as label, train the scoring model, obtain the expression of the geological score of the wind turbine foundation after the training is completed;

[0055] S2. Obtain the geological conditions and soil mechanical parameters of the construction site of the current to-be-built wind turbine foundation, and randomly generate multiple initial combinations of the size of the wind turbine foundation within the range of the maximum and minimum values according to the size of the previous wind turbine foundation. The initial combinations are spliced with the geological conditions and soil mechanical parameters to form an initial population;

[0056] S3. Calculate the wind turbine foundation design score of each individual in the initial population according to the expression of the wind turbine foundation design score. Take the maximization of the wind turbine foundation design score as the optimization goal, and use the genetic algorithm to iteratively optimize the initial population to generate the optimal individual and extract the optimal size of the wind turbine foundation;

[0057] S4. According to the historical changes of the geological conditions and soil mechanical parameters of the current to-be-built wind turbine foundation construction site, calculate the average stability coefficient of the changes, and use the average stability coefficient as the correction coefficient to correct the optimal size.

[0058] On the basis of the above embodiment, the size of the wind turbine foundation includes diameter and height, the geological conditions include ground elevation and underground water level, and the soil mechanical parameters include soil density, porosity, shear strength and compressive strength.

[0059] The collection methods of diameter, height, ground elevation, underground water level, soil density, porosity, shear strength and compressive strength are as follows:

[0060] Use a measuring scale to measure the diameter of the wind turbine foundation;

[0061] Obtain the vertical height of the outside of the wind turbine foundation by measuring scale;

[0062] Use Global Positioning System (GPS) or laser range finder to measure the ground elevation at different positions;

[0063] Use the underground water level monitoring well or water level sensor to regularly measure the depth and changes of the underground water level;

[0064] Collect soil samples and use soil density meter and porosity measuring instrument to measure soil density and porosity;

[0065] Perform soil mechanical test, use shear testing machine and compaction tester to measure soil shear strength and compressive strength.

[0066] On the basis of the above embodiment, use the collected diameter of the wind turbine foundation, height of the wind turbine foundation, and ground elevation, underground water level, soil density, porosity, shear strength and compressive strength to calculate the geological score of the wind turbine foundation. The obtained expression formula of the wind turbine foundation design score is as follows:

[0067]

[0068] wherein PF is the geological score of the fan foundation, D is the diameter of the fan foundation, H is the height of the fan foundation, E is the ground elevation, W is the underground water level, M is the soil density, K is the porosity, J is the shear strength, Q is the compressive strength, a is the weight coefficient of the diameter of the fan foundation, b is the weight coefficient of the height of the fan foundation, g is the weight coefficient of the ground elevation, k is the weight coefficient of the underground water level, l is the weight coefficient of the soil density, m is the weight coefficient of the porosity, w is the weight coefficient of the shear strength, Q is the weight coefficient of the compressive strength;

[0069] Larger diameter and height can provide better stability and carrying capacity, so the diameter D and the height H are positively correlated with the geological score PF; lower ground elevation can provide a more stable foundation and reduce geological risks, so the ground elevation E is negatively correlated with the geological score PF; higher underground water level can cause soil saturation and liquefaction, increasing the instability and carrying risk of the foundation, so the underground water level W is negatively correlated with the geological score PF; higher soil density and lower porosity can provide better foundation support and carrying capacity, so the soil density M and the porosity K are positively correlated with the geological score PF; higher shear strength J and compressive strength Q can provide better foundation stability and carrying capacity, so the shear strength and the compressive strength are positively correlated with the geological score PF.

[0070] Since the diameter of the fan foundation, the height of the fan foundation, the ground elevation, the underground water level, the soil density, the porosity, the shear strength, and the compressive strength are all linearly related to the geological score of the fan foundation, the above linear function can be used to represent the functional relationship between the diameter D of the fan foundation, the height H of the fan foundation, the ground elevation E, the underground water level W, the soil density M, the porosity K, the shear strength J, the compressive strength Q, and the geological score PF of the fan foundation.

[0071] The compressive strength Q refers to the ability of the foundation to withstand pressure, which directly affects the carrying capacity of the foundation, so it has a greater impact on the geological score PF; the diameter D and the height H of the fan foundation directly affect the stability and carrying capacity of the foundation, but in general, the compressive strength has a more direct and important impact on the geological score, and the diameter D and the height H of the fan foundation have a comparable impact on the geological score of the fan foundation, so The soil density M and the shear strength J are directly related to the bearing capacity and stability of the soil, and thus have a greater impact on the geological score PF. However, the diameter D and the height H of the fan foundation have a smaller impact on the geological score PF. Moreover, the soil density M has a greater impact on the geological score PF of the fan foundation than the shear strength J, because the soil density M directly affects the bearing capacity and stability of the soil, while the shear strength J mainly reflects the shear performance of the soil, and has a relatively small impact on the foundation. Therefore, in general cases, the weight coefficient λ of the soil density M is greater than the weight coefficient ω of the shear strength J, and thus β>λ>ω is set. The ground elevation E affects the stability and geological conditions of the foundation, and thus has a certain impact on the geological score PF. However, the impact of the ground elevation E on the geological score PF is relatively small compared with the impact of the shear strength on the geological score PF, and thus ω>γ is set. The porosity is the proportion of pores in the soil, and directly affects the compactness and bearing capacity of the soil. The porosity K refers to the ratio of the occupied volume of pores in the soil to the total volume, and is a parameter for describing the compactness of the soil. Compared with the ground elevation E, the porosity K more reflects the physical properties of the soil, rather than directly affecting the bearing capacity and stability of the foundation. Therefore, the impact of the porosity K on the geological score PF is smaller than the impact of the ground elevation E on the geological score PF, and thus γ>μ is set. The underground water level W directly affects the saturation state and bearing capacity of the soil. However, the impact of the underground water level W on the geological score PF is smaller than the impact of the porosity K on the geological score PF, and thus μ>κ is set.

[0072] In summary, β>λ>ω>γ>μ>κ is set. In the absence of the influence of other parameters, β>λ>ω>γ>μ>κ is set.

[0073] On the basis of the above embodiment, the scoring model adopts a convolutional neural network model, which is constituted by a multilayer perceptron-based deep neural network. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons, and each adopts ReLU as an activation function.

[0074] In this embodiment, the input features of the deep neural network of the multilayer perceptron include the diameter D of the fan foundation, the height H of the fan foundation, the ground elevation E, the underground water level W, the soil density M, the porosity K, the shear strength J, and the compressive strength Q, i.e., 8 features.

[0075] The structure of the deep neural network of the multilayer perceptron is as follows:

[0076] The input layer receives the input of 8 features;

[0077] The first hidden layer has 128 neurons, and uses ReLU as an activation function;

[0078] Second hidden layer: with 256 neurons, also using ReLU activation function;

[0079] Third hidden layer: with 128 neurons, using ReLU activation function;

[0080] Output layer: with a single neuron, the geological score of the fan foundation PF.

[0081] On the basis of the above embodiment, the geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation are obtained, and a plurality of initial combinations of the size of the fan foundation are generated according to the size of the previous fan foundation, and the specific process is as follows:

[0082] The geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation are collected, including ground elevation E, underground water level W, soil density M, porosity K, shear strength J, and compressive strength Q, the jth initial combination is marked as Bj, j is the index of the initial combination, and j [1, m], m is the number of initial combinations, and Bj = {Dj, Hj}, Dj and Hj represent the diameter and height in the jth initial combination respectively, the initial population formed by splicing is marked as A, and the initial population A = {A1, A2, …, Aj, …, Am}, Aj is the jth individual in the initial population, and Aj = {E,, W,, M,, K,, J,, Q,, Dj, Hj}.

[0083] On the basis of the above embodiment, the initial population A is iteratively optimized, that is, the individuals in the initial population A are selected, crossed, and mutated, specifically, the fan foundation design score values are arranged in descending order of numerical value, the individuals with the top fan foundation design score values are selected as the parents, the genes of the parent individuals are exchanged and combined through the crossover operation to generate new individuals, and after the genes of the diameter and height in the newly generated individuals are mutated, the selection, crossover and mutation operations are repeated until the stopping condition (such as reaching the maximum number of iterations or finding a satisfactory solution) is reached, and the top refers to the individuals in the top 50% of the fan foundation design score values.

[0084] After the initial population A is iteratively optimized, the optimal individual is marked as Aj1 = {E,, W,, M,, K,, J,, Q,, Dj1, Hj1}, and the optimal size of the wind power foundation is diameter Dj1 and height Hj1. On the basis of the above embodiment, the stability coefficient of the change of the geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation is calculated according to the historical change, and the specific process is as follows:

[0085] The geological conditions and soil mechanical parameters of the to-be-built fan foundation construction site at T collection time points in the historical period are collected, that is:

[0086] E, = {E, (1), E, (2), …, E, (t), …, E, (T)}

[0087] W, = {W, (1), W, (2), …, W, (t), …, W, (T)}

[0088] M, = {M, (1), M, (2), …, M, (t), …, M, (T)}

[0089] K, = {K, (1), K, (2), …, K, (t), …, K, (T)}

[0090] J, = {J, (1), J, (2), …, J, (t), …, J, (T)}

[0091] Q, = {Q, (1), Q, (2), …, Q, (t), …, Q, (T)}

[0092] Wherein, E, (t) is the to-be-built wind turbine foundation construction site at the tth collection time Ground elevation, W, (t) is the to-be-built wind turbine foundation construction site at the tth collection time Groundwater level, M, (t) is the to-be-built wind turbine foundation construction site at the tth collection time Soil density, K, (t) is the to-be-built wind turbine foundation construction site at the tth collection time Porosity, J, (t) is the to-be-built wind turbine foundation construction site at the tth collection time Shear strength, Q, (t) is the to-be-built wind turbine foundation construction site at the tth collection time Compressive strength.

[0093] The stability coefficients of each parameter and the average stability coefficient are obtained according to the following formula:

[0094]

[0095] PS = (ES + WS + MS + KS + JS + QS) / 6

[0096] Wherein, ES is the stability coefficient of the ground elevation of the to-be-built wind turbine foundation construction site, WS is the stability coefficient of the groundwater level of the to-be-built wind turbine foundation construction site, MS is the stability coefficient of the soil density of the to-be-built wind turbine foundation construction site, KS is the stability coefficient of the porosity of the to-be-built wind turbine foundation construction site, JS is the stability coefficient of the shear strength of the to-be-built wind turbine foundation construction site, QS is the stability coefficient of the compressive strength of the to-be-built wind turbine foundation construction site, and PS is the average stability coefficient.

[0097] On the basis of the above embodiment, the average stability coefficient PS is taken as a correction coefficient to correct the optimal size, and the formula is as follows:

[0098] D, j1 = Dj1 x PS

[0099] H, j1 = Hj1 x PS

[0100] wherein D,j1 is the modified diameter of the fan foundation, and H,j1 is the modified height of the fan foundation.

[0101] In the formula The specific values of α, β, λ, ω, γ, μ, and κ are generally determined by a person skilled in the art according to actual conditions. The formula is essentially a comprehensive analysis by weighted summation. A person skilled in the art collects multiple sets of sample data, sets a corresponding weight coefficient for each set of sample data, substitutes the set weight coefficient and the collected sample data into the formula, and gradually adjusts the weight coefficients by repeatedly testing and adjusting parameters, observes the accuracy of the model output and the rationality of the results, gradually adjusts the weight coefficients, compares the performance and effects of the model under different parameter settings, finds the optimal combination of weights, filters the calculated weight coefficients and takes the mean value to obtain The values of α, β, λ, ω, γ, μ, and κ.

[0102] In addition, the size of the weight coefficient is a specific numerical value obtained by quantifying each parameter. In order to facilitate subsequent comparison, the size of the weight coefficient depends on the number of sample data and the corresponding weight coefficient initially set by a person skilled in the art for each set of sample data, and is not unique. As long as it does not affect the proportional relationship between the parameters and the quantized numerical value.

[0103] Please refer to Figure 2 The application also provides a technical solution:

[0104] An intelligent design system for a fan foundation of a wind farm, which is used to perform the intelligent design method for a fan foundation of a wind farm as described in any of the above, and comprises:

[0105] A score acquisition module is configured to acquire the size of a past fan foundation and the geological conditions and soil mechanical parameters of the construction site thereof, and score the same by an expert group, take the size and the geological conditions and soil mechanical parameters of the construction site thereof as inputs, take the score as a label, train a scoring model, obtain an expression of the geological score of the fan foundation after the training of the model is completed, and acquire the expression of the geological score of the fan foundation.

[0106] A data processing module is configured to acquire the geological conditions and soil mechanical parameters of a current construction site of a to-be-built fan foundation, and generate multiple initial combinations of the size of the fan foundation according to the size of the past fan foundation, splice the initial combinations with the geological conditions and soil mechanical parameters to form an initial population.

[0107] A size optimization module is configured to calculate the fan foundation design score of each individual in the initial population according to the expression of the fan foundation design score, take the maximization of the fan foundation design score as an optimization target, perform iterative optimization on the initial population by using a genetic algorithm, generate an optimal individual, and extract the optimal size of the fan foundation.

[0108] The correction module is used for obtaining the average stability coefficient of the change according to the historical change of the geological condition and the soil mechanics parameter of the current site to be built, and correcting the optimal size by taking the average stability coefficient as a correction coefficient.

[0109] The above formulas are all dimensionless values, and the formulas are obtained by collecting a large amount of data to simulate a formula of the latest real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0110] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0111] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0112] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A wind farm wind turbine foundation intelligent design method, characterized in that, The specific steps include: S1. Obtain the size of the previous fan foundation and the geological conditions and soil mechanical parameters of its construction site, and score them by an expert group. Use the size and the geological conditions and soil mechanical parameters of its construction site as inputs, the score as a label, and train the scoring model to obtain a trained model. Obtain the expression of the fan foundation design score; S2. Obtain the geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation, and generate multiple initial combinations of the size of the fan foundation according to the size of the previous fan foundation. The initial combinations are spliced with the geological conditions and soil mechanical parameters to form an initial population; S3. Calculate the fan foundation design score of each individual in the initial population according to the expression of the fan foundation design score. Maximize the fan foundation design score as the optimization objective, and use the genetic algorithm to iteratively optimize the initial population to generate the optimal individual. Extract the optimal size of the wind power foundation; S4. According to the historical changes of the geological conditions, soil mechanical parameters and environmental parameters of the current construction site of the to-be-built fan foundation, calculate the stability of the changes, and use the stability as a correction number to correct the optimal size; The diameter of the fan foundation, the height of the fan foundation, and the ground elevation, groundwater level, soil density, porosity, shear strength, and compressive strength are used to calculate the geological score of the fan foundation. The obtained fan foundation design score expression is as follows: wherein, is a geological score for the wind turbine foundation, is a diameter of the wind turbine foundation, is a height of the wind turbine foundation, is a ground elevation, is a groundwater level, is a soil density, is a porosity, is a shear strength, is a compressive strength, is a weight coefficient for the diameter of the wind turbine foundation, is a weight coefficient for the height of the wind turbine foundation, is a weight coefficient for the ground elevation, is a weight coefficient for the groundwater level, is a weight coefficient for the soil density, is a weight coefficient for the porosity, is a weight coefficient for the shear strength, is a weight coefficient for the compressive strength, , .

2. The method of claim 1, wherein: The scoring model uses a convolutional neural network model, which is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer each have at least two neurons and use ReLU as the activation function.

3. The method of claim 2, wherein: Obtain the geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation, and generate multiple initial combinations of the size of the fan foundation according to the size of the previous fan foundation. The specific process is as follows: Collect the geological conditions and soil mechanics parameters of the current to-be-built wind turbine foundation construction site, including ground elevation , underground water level , soil density , porosity , shear strength , compressive strength , the jth initial combination is marked as , j is the index of the initial combination, and , m is the number of initial combinations, and , respectively represent the diameter and height in the jth initial combination, the initial population formed by splicing is marked as A, and the initial population , is the jth individual in the initial population, and .

4. The method of claim 3, wherein: The initial population Iterative optimization is performed, that is, selection, crossover and mutation operations are performed on individuals in the initial population Specifically, individuals with top scores of fan foundation design are selected as parents, and genes of the parent individuals are exchanged and combined through a crossover operation to generate new individuals. After mutation operations are performed on the diameter and height genes in the new individuals, the selection, crossover and mutation operations are repeatedly performed until a stop condition is reached. After the iterative optimization on the initial population , the optimal individual is calibrated as , and the optimal size of the wind power foundation is diameter , height .

5. The method of claim 4, wherein: According to the historical changes of the geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation, calculate the stability coefficient of the changes. The specific process is as follows: Collect the geological conditions and soil mechanical parameters of the to-be-built fan foundation construction site at T collection times in the historical period, i.e. wherein, is the ground elevation at the tth collection time in the construction site of the wind turbine foundation, is the underground water level at the tth collection time in the construction site of the wind turbine foundation, is the soil density at the tth collection time in the construction site of the wind turbine foundation, is the porosity at the tth collection time in the construction site of the wind turbine foundation, is the shear strength at the tth collection time in the construction site of the wind turbine foundation, is the compressive strength at the tth collection time in the construction site of the wind turbine foundation.

6. The method of claim 5, wherein: Calculate the stability coefficient of each parameter and the average stability coefficient according to the following formula: wherein, is a stability coefficient of the ground elevation of the construction site of the wind turbine foundation to be built, is a stability coefficient of the groundwater level of the construction site of the wind turbine foundation to be built, is a stability coefficient of the soil density of the construction site of the wind turbine foundation to be built, is a stability coefficient of the porosity of the construction site of the wind turbine foundation to be built, is a stability coefficient of the shear strength of the construction site of the wind turbine foundation to be built, is a stability coefficient of the compressive strength of the construction site of the wind turbine foundation to be built, is an average stability coefficient.

7. The method of claim 6, wherein: The average stability coefficient As the correction coefficient, the optimum size is corrected according to the following formula: wherein, Df is the diameter of the modified fan foundation, Hf is the height of the modified fan foundation. 8.A system for intelligent design of wind turbine foundations of a wind farm, the system being configured to perform a method for intelligent design of wind turbine foundations of a wind farm according to any one of claims 1 to 7. It includes: The scoring acquisition module is used to obtain the size of the previous fan foundation and the geological conditions and soil mechanical parameters of its construction site, and score them by an expert group. Use the size and the geological conditions and soil mechanical parameters of its construction site as inputs, the score as a label, and train the scoring model to obtain a trained model. Obtain the expression of the fan foundation geological score; The data processing module is used to obtain the geological conditions and soil mechanical parameters of the current construction site of the to-be-built fan foundation, and generate multiple initial combinations of the size of the fan foundation according to the size of the previous fan foundation. The initial combinations are spliced with the geological conditions and soil mechanical parameters to form an initial population; The size optimization module is used for calculating the wind turbine foundation design score of each individual in the initial population according to an expression of the wind turbine foundation design score, taking the maximization of the wind turbine foundation design score as an optimization target, and generating an optimal individual by iteratively optimizing the initial population by using a genetic algorithm, and extracting the optimal size of the wind power foundation; The correction module is used for calculating the average stability coefficient of the change according to the geological conditions and the historical change of the soil mechanical parameters of the construction site of the wind turbine foundation to be built, taking the average stability coefficient as a correction coefficient, and correcting the optimal size.

Images