Intelligent design method and system for wind power plant fan foundation

Abstract

The invention provides an intelligent design method and system for a wind power plant fan foundation, and relates to the technical field of fan foundation design, and the method specifically comprises the steps: obtaining the size, geological conditions, soil mechanical parameters and environmental parameters of a previous fan foundation, and carrying out the evaluation through expert scoring; according to the previous data and the scoring model, generating a plurality of initial combinations of the wind turbine basic size; carrying out iterative optimization on the initial combination by utilizing a genetic algorithm to obtain an optimal fan basic design size; according to historical changes of geological conditions, soil mechanical parameters and environmental parameters of the current to-be-built fan infrastructure construction site, calculating an average stability coefficient of the changes; and correcting the optimal size by using the average stability coefficient so as to adapt to the requirements of the actual environment. Quantitative evaluation of site conditions and environmental parameters is achieved, the influence of the site conditions and the environmental parameters on the basic performance of the draught fan is accurately reflected, the design parameters are intelligently adjusted according to the requirements of the actual environment, and the design result is more suitable for the actual environment.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine foundation design, and in particular to an intelligent design method and system for wind turbine foundations in a wind farm. Background Art

[0002] The intelligent design method and system of wind turbine foundation in wind farms refers to the intelligent and automated design of wind turbine foundation by using technologies such as artificial intelligence, big data analysis, and machine learning. Such methods and systems can help engineers and designers design wind turbine foundations more quickly and accurately, and improve design efficiency and quality.

[0003] In the prior art, the publication number CN115470650A discloses a method and device for automatically designing the foundation of a wind turbine in a wind farm. For shallow buried foundations, this method uses multiple iterative calculations to calculate the design results of the foundation of the wind turbine, and finally calculates the design results and engineering quantities of the foundation of the wind turbine. For deep foundations, the preset foundation engineering quantities are automatically matched, and then the design results are matched according to the load range, and the pile foundation design results are matched according to the geological conditions, and finally the design results and engineering quantities of the foundation of the wind turbine are calculated. This method is highly operational, improves the degree of automated design of the foundation of a wind turbine in a wind farm, and greatly reduces the process of designing the foundation of the wind turbine while meeting the requirements of the reliability of the bearing capacity of the foundation of the wind turbine. It has strong engineering applicability and is suitable for the automatic design of the foundation of the wind turbine in the domestic and foreign wind power industries, filling the gap in the field of automatic design and engineering quantity calculation of the foundation of the wind turbine in a wind farm.

[0004] However, there are still the following deficiencies: As can be seen from the above statements, the existing technology has not specifically quantified the impact of site conditions and environmental parameters on the wind turbine foundation, but the performance of the wind turbine foundation under different geological conditions and environmental influences varies significantly, and the scheme fails to intelligently adjust the design parameters according to the actual situation, so that the design results cannot adapt to the requirements of the actual environment. It adopts static design standards and fails to consider the comprehensive application of real-time monitoring data and historical data, which limits the optimization design and stability evaluation of the wind turbine foundation.

[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 an intelligent design method and system for wind turbine foundations in a wind farm, so as to solve the problems raised in the above-mentioned background technology.

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

[0008] A method for intelligent design of wind turbine foundations in a wind farm, the specific steps comprising:

[0009] S1. Obtain the dimensions of wind turbine foundations in the past, the geological conditions of their construction sites, and the soil mechanical parameters, and have an expert group score them. The dimensions, the geological conditions of their construction sites, and the soil mechanical parameters are used as inputs, and the scores are used as labels to train the scoring model. After the training is completed, the expression of the wind turbine foundation design score is obtained.

[0010] S2. Obtain the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site, and generate multiple initial combinations of wind turbine foundation sizes based on previous wind turbine foundation sizes, and splice the initial combinations with the geological conditions and soil mechanical parameters to form an initial population;

[0011] S3. Calculate the wind turbine foundation design score of each individual in the initial population based on the expression of wind turbine foundation design score, take maximizing the wind turbine foundation design score as the optimization goal, use genetic algorithm to iteratively optimize the initial population, generate the best individual, and extract the optimal size of the wind turbine foundation;

[0012] S4. According to the historical changes of geological conditions, soil mechanical parameters and environmental parameters of the current wind turbine foundation construction site, the stability of the changes is obtained, and the stability is used as a correction factor to correct the optimal size.

[0013] Furthermore, the collected wind turbine foundation diameter, wind turbine foundation height, ground elevation, groundwater level, soil density, porosity, shear strength, and compressive strength are used to calculate the geological score of the wind turbine foundation. The obtained wind turbine foundation design score expression is as follows:

[0014]

[0015] Among them, PF is the geological score of the wind turbine foundation, D is the diameter of the wind turbine foundation, H is the height of the wind turbine foundation, E is the ground elevation, W is the groundwater 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 wind turbine foundation, β is the weight coefficient of the height of the wind turbine foundation, γ is the weight coefficient of the ground elevation, κ is the weight coefficient of the groundwater 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, is the weight coefficient of compressive strength,

[0016] Furthermore, the scoring model adopts a convolutional neural network model, and the convolutional neural network model 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 each uses ReLU as an activation function.

[0017] Furthermore, the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site are obtained, and multiple initial combinations of wind turbine foundation sizes are generated based on the previous wind turbine foundation sizes. The specific process is as follows:

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

[0019] Furthermore, 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 highest wind turbine foundation design score are selected as the parents, and the genes of the parent individuals are exchanged and combined through the crossover operation to generate new individuals. 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 stop condition is reached.

[0020] After iterative optimization of the initial population A, the optimal individual is calibrated as Aj1 = {E,,W,,M,,K,,J,,Q,,Dj1,Hj1}, and the optimal dimensions of the wind turbine foundation are diameter Dj1 and height Hj1.

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

[0022] Collect the geological conditions and soil mechanical parameters of the wind turbine foundation construction site at T collection times in the historical period, that is, the following formula:

[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] Among them, E,(t) is the ground elevation at the t-th collection time in the construction site of the wind turbine foundation to be built, W,(t) is the groundwater level at the t-th collection time in the construction site of the wind turbine foundation to be built, M,(t) is the soil density at the t-th collection time in the construction site of the wind turbine foundation to be built, K,(t) is the porosity at the t-th collection time in the construction site of the wind turbine foundation to be built, J,(t) is the shear strength at the t-th collection time in the construction site of the wind turbine foundation to be built, and Q,(t) is the compressive strength at the t-th collection time in the construction site of the wind turbine foundation to be built.

[0030] Furthermore, the stability coefficient of each parameter and the average stability coefficient are obtained according to the following formula:

[0031]

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

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

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

[0035] D,j1=Dj1×PS

[0036] H,j1=Hj1×PS

[0037] Where D,j1 is the diameter of the corrected fan foundation, and H,j1 is the height of the corrected fan foundation.

[0038] A wind farm wind turbine foundation intelligent design system, the system is used to execute any one of the wind farm wind turbine foundation intelligent design methods as described above, comprising:

[0039] The scoring acquisition module is used to obtain the dimensions of the wind turbine foundation in the past, the geological conditions of the construction site, and the soil mechanical parameters, and to score them through an expert group. The dimensions, the geological conditions of the construction site, and the soil mechanical parameters are used as inputs, and the scores are used as labels to train the scoring model. After the training is completed, the model is obtained to obtain the expression of the geological score of the wind turbine foundation.

[0040] The data processing module is used to obtain the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built, and generate multiple initial combinations of wind turbine foundation sizes based on the previous wind turbine foundation sizes. The initial combinations are spliced ​​with the geological conditions and soil mechanical parameters to form an initial population;

[0041] The size optimization module is used to calculate the wind turbine foundation design score of each individual in the initial population based on the expression of the wind turbine foundation design score, and to maximize the wind turbine foundation design score as the optimization goal. The genetic algorithm is used to iteratively optimize the initial population to generate the optimal individual and extract the optimal size of the wind turbine foundation;

[0042] The correction module is used to obtain the average stability coefficient of the changes based on the geological conditions and historical changes of soil mechanical parameters of the current wind turbine foundation construction site, and use the average stability coefficient as a correction coefficient to correct the optimal size.

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

[0044] The present invention obtains the dimensions of the wind turbine foundation in the past and the geological conditions, soil mechanical parameters and environmental parameters of the construction site, and uses these parameters as input for training through scoring by an expert group to obtain a scoring model, which can achieve quantitative evaluation of site conditions and environmental parameters and accurately reflect their impact on the performance of the wind turbine foundation;

[0045] The initial population is iteratively optimized through genetic algorithms to generate the optimal combination. The average stability coefficient of the changes is obtained based on the historical changes in the geological conditions, soil mechanical parameters and environmental parameters of the current wind turbine foundation construction site. The average stability coefficient is used as a correction factor to correct the optimal size. In this way, the design parameters can be intelligently adjusted according to the requirements of the actual environment, making the design results more suitable for the actual environment.

[0046] By obtaining the geological conditions, soil mechanical parameters and environmental parameters of the current wind turbine foundation construction site, and combining historical data to train and optimize the scoring model, we can fully utilize the comprehensive application of real-time monitoring data and historical data to improve the accuracy of the optimization design and stability assessment of the wind turbine foundation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

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

[0049] 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.

[0050] 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.

[0051] Example:

[0052] See also Figure 1 , the present invention provides a technical solution:

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

[0054] S1. Obtain the dimensions of the wind turbine foundation in the past, the geological conditions of the construction site, and the soil mechanical parameters, and have an expert group score them. The dimensions, the geological conditions of the construction site, and the soil mechanical parameters are used as inputs, and the scores are used as labels to train the scoring model. After the training is completed, the model is obtained to obtain the expression of the geological score of the wind turbine foundation.

[0055] S2. Obtain the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built, and randomly generate multiple initial combinations of wind turbine foundation sizes within the range of maximum and minimum values ​​based on the previous wind turbine foundation sizes, and splice the initial combinations 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 based on the expression of wind turbine foundation design score, take maximizing the wind turbine foundation design score as the optimization goal, use genetic algorithm to iteratively optimize the initial population, generate the best individual, and extract the optimal size of the wind turbine foundation;

[0057] S4. According to the geological conditions of the current wind turbine foundation construction site and the historical changes in soil mechanical parameters, the average stability coefficient of the changes is calculated, and the average stability coefficient is used as a correction coefficient to correct the optimal size.

[0058] Based on the above embodiments, the dimensions of the wind turbine foundation include diameter and height, the geological conditions include ground elevation and groundwater level, and the soil mechanical parameters include soil density, porosity, shear strength and compressive strength.

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

[0060] Use a measuring tape to measure the diameter of the fan foundation;

[0061] Obtain the vertical height of the outside of the wind turbine foundation using a measuring tape;

[0062] Use a global positioning system (GPS) or laser rangefinder to measure ground elevation at different locations;

[0063] Use groundwater monitoring wells or water level sensors to regularly measure the depth and changes in groundwater levels;

[0064] Collect soil samples and measure soil density and porosity using a soil densitometer and porosity meter;

[0065] Conduct soil mechanics tests, using shear testers and compaction testers, to measure the shear and compressive strength of the soil.

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

[0067]

[0068] Among them, PF is the geological score of the wind turbine foundation, D is the diameter of the wind turbine foundation, H is the height of the wind turbine foundation, E is the ground elevation, W is the groundwater 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 wind turbine foundation, β is the weight coefficient of the height of the wind turbine foundation, γ is the weight coefficient of the ground elevation, κ is the weight coefficient of the groundwater 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, is the weight coefficient of compressive strength;

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

[0070] Since the diameter of the fan foundation, the height of the fan foundation, the ground elevation, the groundwater 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-mentioned linear function can be used to characterize the functional relationship between the diameter D of the fan foundation, the height H of the fan foundation, the ground elevation E, the groundwater 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 is directly related to the bearing capacity of the foundation, so it has a greater impact on the geological score PF; the diameter D and height H of the fan foundation directly affect the stability and bearing capacity of the foundation, but in general, the compressive strength will have a more direct and important impact on the geological score. The diameter D and height H of the fan foundation have a similar impact on the geological score of the fan foundation, so Soil density M and shear strength J are directly related to the bearing capacity and stability of the soil, so they have a greater impact on the geological score PF, but have a smaller impact on the geological score PF than the diameter D and height H of the wind turbine foundation, and the impact of soil density M on the geological score PF of the wind turbine foundation is greater than that of shear strength J, because soil density M directly affects the bearing capacity and stability of the soil, while shear strength J mainly reflects the shear resistance of the soil and has a relatively small impact on the foundation. Therefore, under normal circumstances, the weight coefficient λ of soil density M will be greater than the weight coefficient ω of shear strength J, so β>λ>ω is set; ground elevation E will affect the stability and geological conditions of the foundation, so it also has a certain impact on the geological score PF. However, compared with the shear strength, its impact on the geological score PF is relatively small. Therefore, ω>γ is set; porosity is the proportion of pores in the soil, which directly affects the density and bearing capacity of the soil. Porosity K refers to the ratio of the occupied volume of pores in the soil to the total volume. It is a parameter that describes the density of the soil. Compared with the ground elevation E, the porosity K reflects the physical properties of the soil more, rather than directly affecting the bearing capacity and stability of the foundation. Therefore, the porosity K has less impact on the geological score PF than the ground elevation E, and γ>μ is set; the groundwater level W has a direct impact on the saturation state and bearing capacity of the soil, but has a smaller impact on the geological score PF than the porosity K. Therefore, μ>κ is set.

[0072] In summary, setting When no other parameters are affected, set

[0073]

[0074] Based on the above embodiment, the scoring model adopts a convolutional neural network model, and the convolutional neural network model 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 each uses ReLU as an activation function.

[0075] In this embodiment, the input features of the deep neural network of the multilayer perceptron include eight features: diameter D of the wind turbine foundation, height H of the wind turbine foundation, ground elevation E, groundwater level W, soil density M, porosity K, shear strength J, and compressive strength Q.

[0076] The structure of a deep neural network with a multilayer perceptron is:

[0077] Input layer**: receives input of 8 features;

[0078] The first hidden layer has 128 neurons and uses ReLU as the activation function.

[0079] The second hidden layer has 256 neurons and also uses the ReLU activation function.

[0080] The third hidden layer has 128 neurons and uses the ReLU activation function.

[0081] Output layer: has a single neuron, the fan-based geological score PF.

[0082] On the basis of the above embodiment, the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built are obtained, and multiple initial combinations of wind turbine foundation sizes are generated according to the previous wind turbine foundation sizes. The specific process is as follows:

[0083] Collect the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site, including ground elevation E, groundwater level W, soil density M, porosity K, shear strength J, and compressive strength Q, and mark the j-th initial combination as Bj, where j is the index of the initial combination, and j∈[1,m], m is the number of initial combinations, and Bj={Dj,Hj}, Dj,Hj represent the diameter and height in the j-th initial combination respectively, and mark the initial population formed by splicing as A, and the initial population A={A1,A2,…,Aj,…,Am}, Aj is the j-th individual in the initial population, and Aj={E,,W,,M,,K,,J,,Q,,Dj,Hj}.

[0084] 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 wind turbine foundation design score values ​​are arranged from large to small, and the individuals with wind turbine foundation design score values ​​in the top column are selected as parents. Through the crossover operation, the genes of the parent individuals are exchanged and combined to generate new individuals. 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 is reached (such as reaching the maximum number of iterations or finding a satisfactory solution). The top column refers to the individuals in the top 50% of the wind turbine foundation design score values.

[0085] After iterative optimization of the initial population A, the optimal individual is calibrated 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. Based on the above embodiment, according to the geological conditions of the current construction site of the wind turbine foundation and the historical changes of soil mechanical parameters, the stability coefficient of its change is obtained. The specific process is as follows:

[0086] Collect the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built at T collection times in the historical period, that is, the following formula:

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

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

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

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

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

[0092] Q,={Q,(1),Q,(2),…,Q,(t),…,Q,(T)}

[0093] Among them, E,(t) is the ground elevation at the t-th collection time in the construction site of the wind turbine foundation to be built, W,(t) is the groundwater level at the t-th collection time in the construction site of the wind turbine foundation to be built, M,(t) is the soil density at the t-th collection time in the construction site of the wind turbine foundation to be built, K,(t) is the porosity at the t-th collection time in the construction site of the wind turbine foundation to be built, J,(t) is the shear strength at the t-th collection time in the construction site of the wind turbine foundation to be built, and Q,(t) is the compressive strength at the t-th collection time in the construction site of the wind turbine foundation to be built.

[0094] The stability coefficient of each parameter and the average stability coefficient are obtained according to the following formula:

[0095]

[0096] PS=(ES+WS+MS+KS+JS+QS) / 6

[0097] Among them, ES is the stability coefficient of the ground elevation of the construction site of the wind turbine foundation to be built, WS is the stability coefficient of the groundwater level of the construction site of the wind turbine foundation to be built, MS is the stability coefficient of the soil density of the construction site of the wind turbine foundation to be built, KS is the stability coefficient of the porosity of the construction site of the wind turbine foundation to be built, JS is the stability coefficient of the shear strength of the construction site of the wind turbine foundation to be built, QS is the stability coefficient of the compressive strength of the construction site of the wind turbine foundation to be built, and PS is the average stability coefficient.

[0098] On the basis of the above embodiment, the average stability coefficient PS is used as a correction coefficient to correct the optimal size according to the following formula:

[0099] D,j1=Dj1×PS

[0100] H,j1=Hj1×PS

[0101] Where D,j1 is the diameter of the corrected fan foundation, and H,j1 is the height of the corrected fan foundation.

[0102] in the formula The specific values ​​of α, β, λ, ω, γ, μ, and κ are generally determined by those skilled in the art according to actual conditions. The essence of this formula is to perform comprehensive analysis by weighted summation. Those skilled in the art collect multiple groups of sample data, and set corresponding weight coefficients for each group of sample data. The set weight coefficients and the collected sample data are substituted into the formula. Through repeated experiments and parameter adjustments, the accuracy of the model output and the rationality of the results are observed, and these weight coefficients are gradually adjusted. The performance and effect of the model under different parameter settings are compared to find the optimal coefficient combination, and the calculated weight coefficients are screened and averaged to obtain Values ​​of α, β, λ, ω, γ, μ, κ.

[0103] In addition, the size of the weight coefficient is a specific value obtained by quantifying each parameter. In order to facilitate subsequent comparison, the size of the weight coefficient depends on the amount of sample data and the technical personnel in this field preliminarily set the corresponding weight coefficient for each set of sample data. It is not unique as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0104] See also Figure 2 , the present invention also provides a technical solution:

[0105] A wind farm wind turbine foundation intelligent design system, the system is used to execute any one of the wind farm wind turbine foundation intelligent design methods as described above, comprising:

[0106] The scoring acquisition module is used to obtain the dimensions of the wind turbine foundation in the past, the geological conditions of the construction site, and the soil mechanical parameters, and to score them through an expert group. The dimensions, the geological conditions of the construction site, and the soil mechanical parameters are used as inputs, and the scores are used as labels to train the scoring model. After the training is completed, the model is obtained to obtain the expression of the geological score of the wind turbine foundation.

[0107] The data processing module is used to obtain the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built, and generate multiple initial combinations of wind turbine foundation sizes based on the previous wind turbine foundation sizes. The initial combinations are spliced ​​with the geological conditions and soil mechanical parameters to form an initial population;

[0108] The size optimization module is used to calculate the wind turbine foundation design score of each individual in the initial population based on the expression of the wind turbine foundation design score, and to maximize the wind turbine foundation design score as the optimization goal. The genetic algorithm is used to iteratively optimize the initial population to generate the optimal individual and extract the optimal size of the wind turbine foundation;

[0109] The correction module is used to obtain the average stability coefficient of the changes based on the geological conditions and historical changes of soil mechanical parameters of the current wind turbine foundation construction site, and use the average stability coefficient as a correction coefficient to correct the optimal size.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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. An intelligent design method for wind turbine foundations in a wind farm, characterized in that: The specific steps include: S1. Obtain the dimensions of wind turbine foundations in the past, the geological conditions of their construction sites, and the soil mechanical parameters, and have an expert group score them. The dimensions, the geological conditions of their construction sites, and the soil mechanical parameters are used as inputs, and the scores are used as labels to train the scoring model. After the training is completed, the expression of the wind turbine foundation design score is obtained. S2. Obtain the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site, and generate multiple initial combinations of wind turbine foundation sizes based on previous wind turbine foundation sizes, and splice the initial combinations with the geological conditions and soil mechanical parameters to form an initial population; S3. Calculate the wind turbine foundation design score of each individual in the initial population based on the expression of wind turbine foundation design score, take maximizing the wind turbine foundation design score as the optimization goal, use genetic algorithm to iteratively optimize the initial population, generate the best individual, and extract the optimal size of the wind turbine foundation; S4. According to the historical changes of geological conditions, soil mechanical parameters and environmental parameters of the current wind turbine foundation construction site, the stability of the changes is obtained, and the stability is used as a correction factor to correct the optimal size.

2. The intelligent design method for wind turbine foundation of a wind farm according to claim 1 is characterized in that: The wind turbine foundation geological score is calculated using the collected wind turbine foundation diameter, wind turbine foundation height, ground elevation, groundwater level, soil density, porosity, shear strength, and compressive strength. The wind turbine foundation design score expression is as follows: Among them, PF is the geological score of the wind turbine foundation, D is the diameter of the wind turbine foundation, H is the height of the wind turbine foundation, E is the ground elevation, W is the groundwater 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 wind turbine foundation, β is the weight coefficient of the height of the wind turbine foundation, γ is the weight coefficient of the ground elevation, κ is the weight coefficient of the groundwater 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, is the weight coefficient of compressive strength, 3. The intelligent design method for wind turbine foundation of a wind farm according to claim 2 is characterized in that: The scoring model adopts a convolutional neural network model, and the convolutional neural network model 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 each uses ReLU as an activation function.

4. The intelligent design method for wind turbine foundation of a wind farm according to claim 3 is characterized by: The geological conditions and soil mechanical parameters of the current wind turbine foundation construction site are obtained, and multiple initial combinations of wind turbine foundation sizes are generated based on the previous wind turbine foundation sizes. The specific process is as follows: Collect the geological conditions and soil mechanical parameters of the current wind turbine foundation construction site, including ground elevation E, groundwater level W', soil density M', porosity K', shear strength J', and compressive strength Q', and calibrate the jth initial combination as B j , j is the index of the initial combination, and j∈[1,m], m is the number of initial combinations, and B j ={D j ,H j }, D j ,H j denote the diameter and height of the jth initial combination respectively, and the initial population formed by splicing is denoted as A, and the initial population A={A1,A2,…,A j ,…,A m }, A j is the jth individual in the initial population, and A j ={E',W',M',K',J',Q',D j ,H j }.

5. The intelligent design method for wind turbine foundation of a wind farm according to claim 4 is characterized in that: Iterative optimization is performed on the initial population A, that is, selection, crossover, and mutation operations are performed on the individuals in the initial population A. Specifically, individuals with the highest wind turbine foundation design score are selected as parents, and the genes of the parent individuals are exchanged and combined through crossover operations to generate new individuals. After mutation operations are performed on the genes of the diameter and height of the newly generated individuals, the selection, crossover, and mutation operations are repeated until the stopping condition is reached; After iterative optimization of the initial population A, the best individual is labeled as A j1 ={E',W',M',K',J',Q',D j1 ,H j1 }, the optimal size of the wind power foundation is diameter D j1 , height H j1 .

6. The intelligent design method for wind turbine foundation of a wind farm according to claim 5 is characterized by: According to the geological conditions of the site where the wind turbine foundation is to be built and the historical changes in soil mechanical parameters, the stability coefficient of the changes is obtained. The specific process is as follows: Collect the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built at T collection times in the historical period, that is, the following formula: Among them, E'(t) is the ground elevation at the tth collection time in the construction site of the wind turbine foundation to be built, W'(t) is the groundwater level at the tth collection time in the construction site of the wind turbine foundation to be built, M'(t) is the soil density at the tth collection time in the construction site of the wind turbine foundation to be built, K'(t) is the porosity at the tth collection time in the construction site of the wind turbine foundation to be built, J'(t) is the shear strength at the tth collection time in the construction site of the wind turbine foundation to be built, and Q'(t) is the compressive strength at the tth collection time in the construction site of the wind turbine foundation to be built.

7. The intelligent design method for wind turbine foundation of a wind farm according to claim 6 is characterized by: The stability coefficient of each parameter and the average stability coefficient are obtained according to the following formula: PS=(ES+WS+MS+KS+JS+QS) / 6 Among them, ES is the stability coefficient of the ground elevation of the construction site of the wind turbine foundation to be built, WS is the stability coefficient of the groundwater level of the construction site of the wind turbine foundation to be built, MS is the stability coefficient of the soil density of the construction site of the wind turbine foundation to be built, KS is the stability coefficient of the porosity of the construction site of the wind turbine foundation to be built, JS is the stability coefficient of the shear strength of the construction site of the wind turbine foundation to be built, QS is the stability coefficient of the compressive strength of the construction site of the wind turbine foundation to be built, and PS is the average stability coefficient.

8. The intelligent design method for wind turbine foundation of a wind farm according to claim 7 is characterized by: The average stability coefficient PS is used as a correction factor to correct the optimal size according to the following formula: D’ j1 =D j1 ×PS H’ j1 =H j1 ×PS Where D,j1 is the diameter of the corrected fan foundation, and H,j1 is the height of the corrected fan foundation.

9. A wind farm wind turbine foundation intelligent design system, the system is used to execute a wind farm wind turbine foundation intelligent design method according to any one of claims 1 to 8, characterized in that: include: The scoring acquisition module is used to obtain the dimensions of the wind turbine foundation in the past, the geological conditions of the construction site, and the soil mechanical parameters, and to score them through an expert group. The dimensions, the geological conditions of the construction site, and the soil mechanical parameters are used as inputs, and the scores are used as labels to train the scoring model. After the training is completed, the model is obtained to obtain the expression of the geological score of the wind turbine foundation. The data processing module is used to obtain the geological conditions and soil mechanical parameters of the construction site of the wind turbine foundation to be built, and generate multiple initial combinations of wind turbine foundation sizes based on the previous wind turbine foundation sizes. The initial combinations are spliced ​​with the geological conditions and soil mechanical parameters to form an initial population; The size optimization module is used to calculate the wind turbine foundation design score of each individual in the initial population based on the expression of the wind turbine foundation design score, and to maximize the wind turbine foundation design score as the optimization goal. The genetic algorithm is used to iteratively optimize the initial population to generate the optimal individual and extract the optimal size of the wind turbine foundation; The correction module is used to obtain the average stability coefficient of the changes based on the geological conditions and historical changes of soil mechanical parameters of the current wind turbine foundation construction site, and use the average stability coefficient as a correction coefficient to correct the optimal size.

Images