Method for constructing digital model of fan foundation based on temperature field and stress field analysis

Abstract

The present invention relates to the field of data processing technology, and in particular to a method for constructing a digital model of a fan foundation based on temperature field stress field analysis, the method comprising: obtaining relevant characteristic data of fan concrete; determining a first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete, and a second correlation degree between the relevant characteristic data and the maximum stress of the fan concrete; determining the degree of influence of the temperature of the fan concrete on the stress of the fan concrete; determining a weight ratio of the temperature and stress of the fan concrete based on the first correlation degree, the second correlation degree and the influence degree; and constructing a digital model of the fan foundation of the fan concrete based on the weight ratio. The method enables the constructed digital model of the fan foundation to more accurately predict the maximum temperature and maximum stress of the fan concrete, thereby improving the prediction accuracy of the digital model of the fan foundation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for constructing a digital model of a fan foundation based on temperature field and stress field analysis in the technical field of data processing. Background Art

[0002] Wind power projects are an important part of clean and renewable energy. The mass concrete foundation in wind power projects is the key to supporting the wind turbine structure. Its quality and stability are directly related to the operational safety and service life of the entire wind farm. However, during the construction of the mass concrete foundation, due to the large temperature difference of the concrete, it is easy to cause excessive stress, which in turn causes cracks in the concrete after solidification. Such cracks will reduce the impermeability and durability of the concrete, leading to structural damage and failure, bringing serious safety hazards and economic losses.

[0003] In wind power projects, the temperature and stress prediction of large-volume concrete foundations is a complex problem involving multiple influencing factors and dynamic changes. Neural networks, as a powerful prediction tool, are widely used because of their ability to handle nonlinear and high-dimensional data. When using neural networks to determine the current temperature and stress, the loss function usually gives the same weight to all output prediction errors, making the constructed digital model of wind turbine foundations less accurate. Summary of the invention

[0004] In order to solve the technical problem of low accuracy of the digital model of the wind turbine foundation constructed in the prior art, the purpose of the present invention is to provide a method for constructing a digital model of the wind turbine foundation based on temperature field and stress field analysis. The technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis, the method comprising:

[0006] Obtain relevant characteristic data of wind turbine concrete;

[0007] determining a first degree of correlation between the relevant characteristic data and a maximum temperature of the wind turbine concrete, and a second degree of correlation between the relevant characteristic data and a maximum stress of the wind turbine concrete;

[0008] Determine the degree to which the temperature of the fan concrete affects the stress of the fan concrete;

[0009] Determining a weight ratio of temperature and stress of the wind turbine concrete based on the first correlation degree, the second correlation degree and the influence degree;

[0010] Based on the weight ratio, a digital model of the fan foundation of the fan concrete is constructed.

[0011] Further, determining a first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete includes:

[0012] Obtain the average temperature value of the highest temperature corresponding to the relevant characteristic data;

[0013] determining a first difference between the maximum temperature and the average temperature values;

[0014] determining a second difference between any one of the relevant characteristic data and an average value of the relevant characteristic data;

[0015] Based on the first difference and the second difference, a first degree of correlation between the relevant characteristic data and the maximum temperature is determined.

[0016] Further, determining a second correlation degree between the relevant characteristic data and the maximum stress of the wind turbine concrete includes:

[0017] Obtain the average stress of the maximum stress corresponding to each relevant characteristic data of the wind turbine concrete;

[0018] determining a third difference between the maximum stress and the mean stress;

[0019] Based on the third difference and the second difference, a second degree of correlation between the relevant characteristic data and the maximum stress is determined.

[0020] Further, the influence of the temperature of the fan concrete on the stress of the fan concrete is determined, including:

[0021] Based on the maximum temperature and maximum stress of the fan concrete, determine the initial influence of the current temperature of the fan concrete on the stress;

[0022] Determine the similarity of the trapezoidal lines based on the trapezoidal line of temperature and the trapezoidal line of stress of the fan concrete;

[0023] Based on the trapezoidal line similarity, the initial influence degree is corrected to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

[0024] Furthermore, based on the trapezoidal line similarity, the initial influence degree is corrected to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete, including:

[0025] Determine the trapezoidal lines of candidate stresses whose trapezoidal line similarity is greater than the initial influence degree;

[0026] Determine a number ratio based on the total number of trapezoidal lines of stress and the number of trapezoidal lines of the candidate stress;

[0027] The initial influence degree is corrected based on the number ratio to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

[0028] Further, based on the first correlation degree, the second correlation degree and the influence degree, a weight ratio of the temperature and stress of the wind turbine concrete is determined, including:

[0029] determining an overall performance degree of the maximum temperature of the fan concrete based on the first correlation degree and the second correlation degree;

[0030] Based on the overall performance and impact of the maximum temperature, the weight ratio of temperature and stress of the fan concrete is determined.

[0031] Further, based on the first correlation degree and the second correlation degree, the overall performance degree of the maximum temperature of the wind turbine concrete is determined, including:

[0032] Fusing the first correlation levels to obtain a first fusion result;

[0033] Fusing the second correlation degree with the first correlation degree to obtain a second fusion result;

[0034] Based on the ratio between the first fusion result and the second fusion result, the overall performance degree of the maximum temperature of the fan concrete is obtained.

[0035] Furthermore, based on the overall performance and influence of the maximum temperature, the weight ratio of temperature and stress of the wind turbine concrete is determined, including:

[0036] The influence degree is adjusted by using a preset adjustment value to obtain an adjusted influence degree;

[0037] Based on the adjusted impact level and the overall performance level of the maximum temperature, the weighted ratio of temperature to stress of the wind turbine concrete is determined.

[0038] Furthermore, based on the weight ratio, a digital model of the fan foundation of the fan concrete is constructed, including:

[0039] Obtaining an initial loss function of an initial wind turbine basic digital model;

[0040] Based on the weight ratio, the initial loss function is corrected to obtain a corrected loss function;

[0041] Based on the corrected loss function, the initial wind turbine basic digital model is adjusted to obtain the wind turbine basic digital model.

[0042] Furthermore, based on the weight ratio, the initial loss function is modified to obtain a modified loss function, including:

[0043] The temperature difference information in the initial loss function is adjusted based on the weight ratio to obtain the adjusted temperature; wherein the temperature difference information is used to represent the difference between the actual temperature and the predicted temperature;

[0044] Based on the difference between the weight ratio and the preset value, the stress difference information in the initial loss function is adjusted to obtain the adjusted stress; wherein the stress difference information is used to characterize the difference between the actual stress and the predicted stress;

[0045] Based on the adjusted temperature and the adjusted stress, a modified loss function is determined.

[0046] In the second aspect, a device for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis is provided, and the device comprises:

[0047] An acquisition module is used to acquire relevant characteristic data of the fan concrete;

[0048] A first determination module is used to determine a first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete, and a second correlation degree between the relevant characteristic data and the maximum stress of the fan concrete;

[0049] The second determination module is used to determine the influence degree of the temperature of the fan concrete on the stress of the fan concrete;

[0050] A third determination module is used to determine a weight ratio of temperature and stress of the wind turbine concrete based on the first correlation degree, the second correlation degree and the influence degree;

[0051] The construction module is used to construct a digital model of the wind turbine foundation of the wind turbine concrete based on the weight ratio.

[0052] According to a third aspect, a computer program product is provided. The computer program product includes: a computer program code. When the computer program code is executed on a computer, the computer executes the method according to the first aspect.

[0053] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program code. When the computer program code is executed on a computer, the computer executes the method according to the first aspect.

[0054] The present invention has the following beneficial effects: after obtaining the relevant characteristic data of the fan concrete, the first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete, and the second correlation degree between the relevant characteristic data and the maximum stress of the fan concrete are determined; in this way, the correlation degree between the maximum temperature and the maximum stress and the relevant characteristic data can be reflected through the first correlation degree and the second correlation degree. Afterwards, the influence degree of the temperature of the fan concrete on the stress of the fan concrete is determined; so as to determine the weight ratio of the temperature and stress of the fan concrete through the first correlation degree, the second correlation degree and the influence degree; in this way, by combining the first correlation degree, the second correlation degree and the influence degree, the weight ratio between the temperature and stress of the fan concrete can be more accurately analyzed, so as to construct the fan foundation digital model of the fan concrete through the weight ratio. In this way, the weight ratio between the temperature and stress of the fan concrete is adjusted through the correlation degree and the influence degree, so that the fan foundation digital model of the fan concrete constructed can more accurately predict the current maximum temperature and the current maximum stress in the fan concrete, thereby improving the prediction accuracy of the fan foundation digital model. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 It is a schematic diagram of the implementation process of the method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0057] Figure 2 It is a schematic diagram of an application scenario of a method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0058] Figure 3 It is a schematic diagram of an application scenario of a method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0059] Figure 4 It is another implementation flow diagram of the method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0060] Figure 5 It is a schematic diagram of another application scenario of the method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0061] Figure 6 It is another application scenario schematic diagram of the method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0062] Figure 7 It is another implementation flow diagram of the method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention;

[0063] Figure 8 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method for constructing a digital model of a fan foundation based on temperature field and stress field analysis proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0065] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0066] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0067] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0068] The following is a detailed description of the specific scheme of the method for constructing a digital model of a fan foundation based on temperature field and stress field analysis provided by the present invention in conjunction with the accompanying drawings. Figure 1 , which shows a flow chart of a method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis provided by an embodiment of the present invention, the method comprising:

[0069] 101, obtaining relevant characteristic data of wind turbine concrete.

[0070] Here, the finite element method is used to calculate the small solid disk, build the model, and obtain the relevant characteristic data of the current wind turbine concrete. Figure 2 As shown, by using finite element calculation of a small solid disk, a finite element model 201 is established; the geometric characteristics of the current wind turbine concrete are abstractly expressed by the finite element model 201, so that the temperature field of the current wind turbine concrete can be predicted by the finite element model 201; another finite element model of the current small solid disk foundation (such as Figure 3 As shown in another finite element model 202 in the figure, the stress field of the current fan concrete is predicted to obtain the relevant characteristic data of the fan concrete. Since this process belongs to the prior art, it will not be described here. The relevant characteristic data of the fan concrete include: the thermodynamic characteristics of the material, such as elastic modulus, linear expansion coefficient, thermal conductivity, adiabatic temperature rise, etc., and also include the temperature conditions of the external environment, the annual average temperature, the annual temperature difference, wind speed, etc., and other related influencing characteristics, such as the construction start date, cement type, cooling time, and cooling method. These relevant characteristic data are very important in predicting the temperature and stress of concrete, and jointly determine the temperature behavior and stress state of the fan concrete during construction and use. By comprehensively considering these factors, the temperature and stress of the fan concrete can be predicted more accurately, so as to formulate effective temperature control and crack prevention measures.

[0071] 102 , determining a first correlation degree between the relevant characteristic data and the maximum temperature of the wind turbine concrete, and a second correlation degree between the relevant characteristic data and the maximum stress of the wind turbine concrete.

[0072] Here, by obtaining the maximum temperature corresponding to each relevant characteristic data, the average temperature value of the maximum temperature is calculated. Afterwards, the first correlation degree between the relevant characteristic data and the maximum temperature of the wind turbine concrete can be accurately analyzed through the difference between the maximum temperature and the average temperature value, and the difference between each relevant characteristic data and the average value of the relevant characteristic data. Similarly, the second correlation degree between the relevant characteristic data and the maximum stress of the wind turbine concrete can be accurately analyzed through the difference between the maximum stress and the average stress value, and the difference between each relevant characteristic data and the average value of the relevant characteristic data.

[0073] In some possible implementations, the relevant characteristic data of different fan concretes have different performances in maximum temperature and maximum stress due to their physical characteristics and other reasons. Some characteristics have a greater impact on the maximum stress, but a smaller impact on the maximum temperature. For example: the elastic modulus directly affects the maximum stress of the fan concrete when the volume changes due to the maximum temperature change. The higher the elastic modulus, the greater the maximum stress change of the fan concrete under the same maximum temperature change; the elastic modulus mainly affects the maximum stress, and has a smaller direct impact on the maximum temperature change inside the fan concrete.

[0074] At the same time, there are also some characteristics that have a small impact on the maximum stress, but a large impact on the maximum temperature. For example, the thermal conductivity determines the efficiency of heat transfer inside the fan concrete. The higher the thermal conductivity, the faster the heat transfer, the more uniform the maximum temperature distribution inside the fan concrete, and the smaller the temperature difference. The thermal conductivity mainly affects the maximum temperature distribution, but has a small direct impact on the maximum stress.

[0075] Therefore, according to the above analysis, it can be determined that different fan characteristics have different degrees of expression on the maximum temperature and maximum stress of the fan concrete. Therefore, it is necessary to determine different correlation degrees through the Pierce coefficient according to the current data of each relevant characteristic, maximum temperature and maximum stress. The "determining the first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete" in the above step 102 can be achieved by the following steps 121 to 124 (not shown in the figure):

[0076] 121, obtaining an average temperature value of the highest temperature corresponding to the relevant characteristic data.

[0077] Here, since the relevant characteristic data includes multiple data, each data corresponds to a maximum temperature that can be tolerated, the maximum temperatures corresponding to the multiple data are averaged to obtain an average temperature value.

[0078] 122, determine a first difference between the maximum temperature and the average temperature value.

[0079] Here, each maximum temperature is subtracted from the average temperature value to obtain a first difference value.

[0080] 123, determine a second difference between any data in the relevant feature data and an average value of the relevant feature data.

[0081] Here, the average value of all relevant feature data belonging to the same category is calculated first, and then the relevant feature data is subtracted from the average value to obtain the second difference.

[0082] 124 , determining a first correlation degree between the relevant characteristic data and the maximum temperature based on the first difference and the second difference.

[0083] Here, by combining the first difference and the second difference, the first correlation degree between the relevant characteristic data and the temperature of the fan concrete can be accurately obtained. In this way, by analyzing the first difference between the maximum temperature and the average temperature value of the maximum temperature, and the second difference between any relevant characteristic data and the average value of the relevant characteristic data, the first correlation degree between the relevant characteristic data and the temperature of the fan concrete can be accurately calculated.

[0084] In the above steps 121 to 124, for the first correlation degree between any type of relevant characteristic data and the current maximum temperature , as shown in formula (1):

[0085] (1);

[0086] Among them, n represents the number of all data in any type of related feature data, represents the maximum temperature that the relevant characteristic data of the i-th fan concrete can reach, It represents the average value of the highest temperature that the fan concrete can reach in all data. represents the i-th data in the v-th related feature data, The average value of the vth related feature data. norm() represents the normalization function, which is used to convert The values ​​are normalized to between 0 and 1.

[0087] In some possible implementations, based on the same principle as steps 121 to 124 above, the “determining the second correlation degree between the relevant characteristic data and the maximum stress of the wind turbine concrete” in step 102 above can be implemented by the following process:

[0088] First, the average stress of the maximum stress corresponding to each relevant characteristic data of the wind turbine concrete is obtained.

[0089] Here, since the relevant characteristic data includes multiple data, each data corresponds to a maximum stress that can be sustained, the maximum stresses corresponding to the multiple data are averaged to obtain the average stress.

[0090] second, determining a third difference between the maximum stress and the mean stress;

[0091] Here, each maximum stress is subtracted from the average stress to obtain a third difference.

[0092] Finally, based on the third difference and the second difference, a second correlation degree between the relevant characteristic data and the maximum stress is determined.

[0093] Here, based on the same principle as formula (1), the second correlation degree between the relevant characteristic data and the maximum stress can be calculated by the third difference and the second difference. In this way, by analyzing the third difference between the maximum stress and the average stress, combined with the second difference between any relevant characteristic data and the average value of the relevant characteristic data, the second correlation degree between the relevant characteristic data and the maximum stress of the wind turbine concrete can be accurately calculated.

[0094] 103, determine the degree of influence of the temperature of the fan concrete on the stress of the fan concrete.

[0095] Here, the influence degree of the temperature of the fan concrete on the stress of the fan concrete can be obtained by first determining the initial influence degree of the current temperature on the stress and then correcting the initial influence degree.

[0096] In some possible implementation methods, during the pouring and hardening process of the fan concrete, the cement hydration reaction will generate a large amount of heat, causing the temperature of the fan concrete to rise. The temperature increase will cause the fan concrete to expand in volume, thus generating stress. When the fan concrete cools, the volume will shrink. Since the surface temperature drops faster than the internal temperature, tensile stress will be generated on the surface. After the fan concrete is poured, it may be necessary to use maintenance measures such as insulation to slow down the heat dissipation rate of the fan concrete, so that the temperature changes inside and on the surface of the fan concrete are more uniform, reducing the stress concentration caused by the temperature gradient. The above step 103 can be completed by Figure 4 The steps shown achieve:

[0097] 301, based on the maximum temperature and maximum stress of the wind turbine concrete, determine the initial influence of the current temperature of the wind turbine concrete on the stress.

[0098] Here, since stress will also change with the change of temperature, but the rapid change of temperature gradient will also have a relatively large impact on stress. So in the same way, the data between the current maximum temperature and the maximum stress are calculated through the Pierce coefficient to determine the initial influence of the current temperature on the stress, recorded as p. For example, according to the relevant characteristic data, the maximum temperatures are arranged in sequence to obtain a maximum temperature sequence, and the maximum stresses are arranged in sequence to obtain a maximum stress sequence. Based on the maximum temperature sequence and the maximum stress sequence, the linear relationship between the data of the current maximum temperature and the maximum stress is evaluated through the Pierce coefficient, and the initial influence of the current temperature on the stress p can be obtained.

[0099] 302 , determining a trapezoidal line similarity based on the trapezoidal line of temperature and the trapezoidal line of stress of the wind turbine concrete.

[0100] Here, since there is a certain difference between the temperature distribution and the stress distribution, it is necessary to determine the difference between the two based on the temperature trapezoidal line.

[0101] like Figure 5 and Figure 6 As shown, curve 401 represents the temperature trapezoidal line of the cross section in the solid disk foundation model, and curve 501 is the stress trapezoidal line of the cross section in the solid disk foundation model corresponding to the current temperature state. Among them, as the temperature increases, the stress increases accordingly. And both are maximum values ​​at the center position in the current disk. For the intersection of the bottom plate and the upper plate in the disk model, the stress changes greatly, and the temperature gradient at this position changes the fastest.

[0102] Depend on Figure 5 and Figure 6 It can be seen that changes in temperature will cause changes in stress, but the changes between the two are not certain, and in the case of shape mutations, the difference between temperature and stress is relatively large, so it is necessary to determine the difference between the two based on the different temperature and stress gradient differences in the current model.

[0103] For the stress trapezoidal line and temperature trapezoidal line of the cross section of any current model, traverse from the gradient line with the highest temperature and the gradient line with the highest stress outward in sequence to determine the similarity between the two gradient lines. That is, the trapezoidal line similarity , as shown in formula (2):

[0104] (2);

[0105] in, represents the dynamic time warping algorithm, used to calculate The dynamic time warping distance between The larger the dynamic time warping distance is, the smaller the corresponding similarity is. The temperature trapezoidal line representing the i-th cross section of the model; Represents the stress trapezoidal line of the i-th cross section of the model.

[0106] 303, based on the trapezoidal line similarity, the initial influence degree is corrected to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

[0107] Here, by analyzing the numerical relationship between the trapezoidal line similarity and the initial influence degree, the stress gradient lines and temperature trapezoidal lines with lower trapezoidal line similarity are determined, and the number ratio between the number of stress gradient lines and the total number of stress gradient lines is calculated. The initial influence degree is adjusted by this number ratio to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

[0108] In some possible implementations, the above step 303 may be implemented by the following steps:

[0109] 331, determine the trapezoidal lines of candidate stresses whose trapezoidal line similarity is greater than the initial influence degree.

[0110] Here, the candidate stress trapezoidal line is the stress whose trapezoidal line similarity is greater than the initial influence degree. If the current trapezoidal line similarity is greater than the initial influence of the current temperature on the stress, it means that there is no similarity between the two.

[0111] 332 , determining a number ratio based on the total number of the trapezoidal lines of stress and the number of the trapezoidal lines of the candidate stress.

[0112] Here, the temperatures and stresses whose trapezoidal line similarity is greater than the initial influence degree are determined, that is, the temperatures and stresses with lower similarity to each other, that is, the candidate temperatures and candidate stresses, are obtained; thus, the number of trapezoidal lines of the candidate stresses can be further counted, and the number ratio can be obtained by dividing the number by the total number of trapezoidal lines of stresses.

[0113] 333, based on the number ratio, the initial influence degree is corrected to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

[0114] Here, according to the currently obtained number ratio, the initial influence of temperature on stress is corrected to obtain the influence of the temperature of the fan concrete on the stress of the fan concrete, as shown in formula (3):

[0115] (3);

[0116] in, Indicates the degree to which the current stress is affected by temperature. is the number of stress gradient lines that do not have similarity, is the total number of stress gradient lines. p represents the initial influence of the modified temperature on the stress.

[0117] 104. Determine a weight ratio of temperature to stress of the wind turbine concrete based on the first correlation degree, the second correlation degree, and the influence degree.

[0118] Here, the weight ratio is the ratio between the weights assigned to temperature and stress. In some possible implementations, the above step 104 can be performed by Figure 7 The steps shown achieve:

[0119] 601 , determining an overall performance level of a maximum temperature of the wind turbine concrete based on the first correlation level and the second correlation level.

[0120] Here, first, each first correlation degree is fused to obtain a first fusion result; for example, each first correlation degree corresponding to each relevant feature data is summed to obtain a first fusion result. Then, the second correlation degree is fused with the first correlation degree to obtain a second fusion result; for example, each second correlation degree is summed with the first correlation degree to obtain a second fusion result. Finally, based on the ratio between the first fusion result and the second fusion result, the overall performance degree of the maximum temperature of the fan concrete is obtained. For example, the first fusion result is divided by the second fusion result to obtain the overall performance degree of the maximum temperature of the fan concrete.

[0121] In some possible implementations, according to the comprehensive value of the correlation between each relevant characteristic data and the maximum stress value and the maximum temperature value, the overall performance level R of the maximum temperature is determined in the input data characteristics of the neural network, as shown in formula (4):

[0122] (4);

[0123] in, represents the first correlation degree between the i-th type of relevant characteristic data and the current maximum temperature; m represents the number of relevant characteristic data; Indicates the second correlation degree between the i-th type of related characteristic data and the current maximum stress value; Indicates the representation degree of the highest temperature among all relevant characteristic data (i.e. the first fusion result); Indicates the relevance of the current maximum temperature in the overall related characteristic data; is the second fusion result.

[0124] 602. Determine the weight ratio of temperature and stress of the wind turbine concrete based on the overall performance and impact of the maximum temperature.

[0125] Here, the influence degree is adjusted by a preset adjustment value to obtain an adjusted influence degree; wherein the preset adjustment value can be a custom value, for example, the preset adjustment value is 1. The preset adjustment value is added to the influence degree to obtain the adjusted influence degree. Afterwards, based on the adjusted influence degree and the overall performance degree of the maximum temperature, the weight ratio of the temperature and stress of the fan concrete is determined. For example, by multiplying the adjusted influence degree and the overall performance degree of the maximum temperature, the weight ratio of the temperature and stress of the fan concrete can be obtained. In this way, the weight ratio of the temperature and stress of the fan concrete can be accurately calculated by combining the overall performance degree of the maximum temperature with the influence degree, thereby facilitating the adjustment of the loss function in the digital model of the fan foundation, thereby improving the prediction accuracy of the digital model of the fan foundation.

[0126] In some possible implementations, the ratio of the difference values ​​of temperature and stress in the re-corrected loss function is determined based on the different characteristic values ​​of the current maximum stress and maximum temperature expressed by the above-mentioned different fan-related data, and the influence of the current temperature on the stress.

[0127] Since it can be determined that the temperature in the wind turbine concrete causes a large change in stress, the loss function can be added to the temperature difference based on the temperature; if the temperature difference is smaller, the corresponding stress difference will also be smaller. The weight ratio of temperature and stress , as shown in formula (5):

[0128] (5);

[0129] in, Indicates the overall performance of temperature in the relevant characteristic data. It indicates the degree to which the current stress is affected by temperature, and norm() indicates the normalization function.

[0130] 105. Based on the weight ratio, a digital model of the fan foundation of the fan concrete is constructed.

[0131] Here, the initial loss function of the initial wind turbine basic digital model is corrected by the weight ratio, so as to obtain the wind turbine basic digital model. In some possible implementations, the above step 105 can be implemented by the following steps 151 to 153 (not shown):

[0132] 151, obtaining an initial loss function of an initial wind turbine basic digital model.

[0133] Here, the initial wind turbine basic digital model is a neural network model for predicting the maximum temperature and maximum stress of the wind turbine. For example, the neural network model can be a convolutional neural network model. , as shown in formula (6):

[0134] (6);

[0135] in, represents the predicted value of temperature, represents the true value of temperature, represents the predicted value of stress, Represents the true value of stress. T in it represents the true value and Y represents the predicted value.

[0136] 152, based on the weight ratio, the initial loss function is corrected to obtain a corrected loss function.

[0137] Here, first, the temperature difference information in the initial loss function is adjusted based on the weight ratio to obtain the adjusted temperature; wherein the temperature difference information is used to characterize the difference between the actual temperature and the predicted temperature; for example, the weight ratio is multiplied by the square of the temperature difference information to obtain the adjusted temperature. Then, based on the difference between the weight ratio and the preset value, the stress difference information in the initial loss function is adjusted to obtain the adjusted stress; wherein the stress difference information is used to characterize the difference between the actual stress and the predicted stress; the preset value can be a custom setting, for example, the preset value is 1. The difference between 1 and the weight ratio is multiplied by the square of the stress difference information to obtain the adjusted stress. Finally, based on the adjusted temperature and the adjusted stress, the corrected loss function is determined. For example, after summing the adjusted temperature and the adjusted stress, the mean square is calculated to obtain the corrected loss function. Corrected loss function As shown in formula (7):

[0138] (7);

[0139] in, Represents the weight ratio of temperature and stress. is the temperature difference information, is the stress difference information.

[0140] 153, based on the corrected loss function, the initial wind turbine basic digital model is adjusted to obtain the wind turbine basic digital model.

[0141] Here, the initial loss function in the initial fan basic digital model is replaced with the corrected loss function; the initial fan basic digital model is trained based on the corrected loss function to obtain the fan basic digital model. For example, a BP neural network is used as the initial fan basic digital model to predict the current maximum stress and maximum temperature based on the current different relevant characteristic data. The input is different relevant characteristic data, and the output is the maximum stress and maximum temperature. After the training is completed, the fan basic digital model is obtained; finally, a validation set or a test set is used to evaluate the performance of the fan basic digital model to check the accuracy of the temperature and stress predicted by the fan basic digital model. In this way, by adjusting the initial loss function through the weight ratio, the prediction accuracy of the constructed fan basic digital model can be higher.

[0142] In an embodiment of the present invention, after obtaining the relevant characteristic data of the fan concrete, the first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete, and the second correlation degree between the relevant characteristic data and the maximum stress of the fan concrete are determined; in this way, the correlation degree between the maximum temperature and the maximum stress and the relevant characteristic data can be reflected through the first correlation degree and the second correlation degree. Afterwards, by combining the first correlation degree, the second correlation degree and the influence degree, the weight ratio between the temperature and stress of the fan concrete can be analyzed more accurately, so as to construct a fan foundation digital model of the fan concrete through the weight ratio. In this way, the weight ratio between the temperature and stress of the fan concrete is adjusted through the correlation degree and the influence degree, so that the fan foundation digital model of the fan concrete constructed can more accurately predict the current maximum temperature and the current maximum stress in the fan concrete, thereby improving the prediction accuracy of the fan foundation digital model.

[0143] The embodiment of the present invention provides a device for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis, the device comprising:

[0144] An acquisition module is used to acquire relevant characteristic data of the fan concrete;

[0145] A first determination module is used to determine a first correlation degree between the relevant characteristic data and the maximum temperature of the fan concrete, and a second correlation degree between the relevant characteristic data and the maximum stress of the fan concrete;

[0146] The second determination module is used to determine the influence degree of the temperature of the fan concrete on the stress of the fan concrete;

[0147] A third determination module is used to determine a weight ratio of temperature and stress of the wind turbine concrete based on the first correlation degree, the second correlation degree and the influence degree;

[0148] The construction module is used to construct a digital model of the wind turbine foundation of the wind turbine concrete based on the weight ratio.

[0149] In some possible implementations, the first determination module is also used to obtain the average temperature value of the highest temperature corresponding to the relevant characteristic data; determine a first difference between the highest temperature and the average temperature value; determine a second difference between any data in the relevant characteristic data and the average value of the relevant characteristic data; and determine a first degree of correlation between the relevant characteristic data and the highest temperature based on the first difference and the second difference.

[0150] In some possible implementations, the first determination module is also used to obtain the average stress of the maximum stress corresponding to each relevant characteristic data of the wind turbine concrete; determine the third difference between the maximum stress and the average stress; and determine the second degree of correlation between the relevant characteristic data and the maximum stress based on the third difference and the second difference.

[0151] In some possible implementations, the second determination module is also used to determine the initial influence of the current temperature of the fan concrete on the stress based on the maximum temperature and maximum stress of the fan concrete; determine the trapezoidal line similarity based on the trapezoidal line of the temperature of the fan concrete and the trapezoidal line of the stress; based on the trapezoidal line similarity, correct the initial influence degree to obtain the influence of the temperature of the fan concrete on the stress of the fan concrete.

[0152] In some possible implementations, the second determination module is also used to determine the trapezoidal lines of candidate temperatures and the trapezoidal lines of candidate stresses whose trapezoidal line similarities are greater than the initial influence degree; determine the number ratio based on the total number of trapezoidal lines of stress and the number of trapezoidal lines of the candidate stress; and correct the initial influence degree based on the number ratio to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

[0153] In some possible implementations, the third determination module is further used to determine the overall performance degree of the maximum temperature of the fan concrete based on the first correlation degree and the second correlation degree; and determine the weight ratio of the temperature and stress of the fan concrete based on the overall performance degree and influence degree of the maximum temperature.

[0154] In some possible implementations, the third determination module is also used to fuse the first correlation degrees to obtain a first fusion result; fuse the second correlation degree with the first correlation degree to obtain a second fusion result; and obtain the overall performance degree of the maximum temperature of the fan concrete based on the ratio between the first fusion result and the second fusion result.

[0155] In some possible implementations, the third determination module is further used to adjust the degree of influence using a preset adjustment value to obtain an adjusted degree of influence; and determine a weight ratio of temperature and stress of the wind turbine concrete based on the adjusted degree of influence and the overall performance of the maximum temperature.

[0156] In some possible implementations, the construction module is also used to obtain an initial loss function of an initial wind turbine basic digital model; based on a weight ratio, the initial loss function is corrected to obtain a corrected loss function; based on the corrected loss function, the initial wind turbine basic digital model is adjusted to obtain a wind turbine basic digital model.

[0157] In some possible implementations, the building module is also used to adjust the temperature difference information in the initial loss function based on the weight ratio to obtain the adjusted temperature; wherein the temperature difference information is used to characterize the difference between the actual temperature and the predicted temperature; based on the difference between the weight ratio and the preset value, the stress difference information in the initial loss function is adjusted to obtain the adjusted stress; wherein the stress difference information is used to characterize the difference between the actual stress and the predicted stress; based on the adjusted temperature and the adjusted stress, the corrected loss function is determined.

[0158] Optionally, the transmission medium may be a wired link (such as but not limited to coaxial cable, optical fiber and digital subscriber line (DSL), etc.) or a wireless link (such as but not limited to wireless Fidelity (WIFI), Bluetooth and mobile device network, etc.). It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the method embodiments provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0159] Figure 8 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 8As shown, the electronic device 700 includes: a memory 701, a processor 702, and a computer program 703 stored in the memory 701 and running on the processor 702, wherein when the processor 702 executes the computer program 703, the device can execute any of the above-mentioned methods for constructing a basic digital model of a wind turbine based on temperature field stress field analysis. In addition, the embodiment of the present invention also protects a device, which may include a memory and a processor, wherein an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute the method for constructing a basic digital model of a wind turbine based on temperature field stress field analysis provided by the embodiment of the present invention.

[0160] This embodiment can divide the functional modules of the device according to the above method example. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0161] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis, so the same effect as the above-mentioned implementation method can be achieved. In the case of an integrated unit, the device may include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logic blocks, modules and circuits described in combination with the contents disclosed in the present invention. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module can be a memory.

[0162] In addition, the device provided in the embodiment of the present invention may be specifically a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the method for constructing a basic digital model of a fan based on temperature field stress field analysis provided in the above embodiment. This embodiment also provides a computer-readable storage medium, in which a computer program code is stored, and when the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement the method for constructing a basic digital model of a fan based on temperature field stress field analysis provided in the above embodiment.

[0163] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement the method for constructing a digital model of a fan foundation based on temperature field stress field analysis provided in the above embodiment. Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here. Through the description of the above implementation mode, the technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiment described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms. It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. The various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A method for constructing a digital model of a fan foundation based on temperature field and stress field analysis, characterized in that: Methods include: Obtain relevant characteristic data of wind turbine concrete, including thermodynamic characteristics of materials and temperature of external environment. The thermodynamic characteristics of materials include elastic modulus, linear expansion coefficient, thermal conductivity and adiabatic temperature rise; determining a first degree of correlation between the relevant characteristic data and a maximum temperature of the wind turbine concrete, and a second degree of correlation between the relevant characteristic data and a maximum stress of the wind turbine concrete; Determine the degree to which the temperature of the fan concrete affects the stress of the fan concrete; Determining a weight ratio of temperature and stress of the wind turbine concrete based on the first correlation degree, the second correlation degree and the influence degree; Based on the weight ratio, a digital model of the fan foundation of the fan concrete is constructed; Determining a first degree of correlation between the relevant characteristic data and the maximum temperature of the fan concrete includes: Obtain the average temperature value of the highest temperature corresponding to the relevant characteristic data; determining a first difference between the maximum temperature and the average temperature values; determining a second difference between any one of the relevant feature data and an average value of the relevant feature data; Determining a first degree of correlation between the relevant characteristic data and the maximum temperature based on the first difference and the second difference; Determine the second degree of correlation between the relevant characteristic data and the maximum stress of the wind turbine concrete, including: Obtain the average stress of the maximum stress corresponding to each relevant characteristic data of the wind turbine concrete; determining a third difference between the maximum stress and the mean stress; Determining a second degree of correlation between the relevant characteristic data and the maximum stress based on the third difference and the second difference; Based on the first correlation degree, the second correlation degree and the influence degree, the weight ratio of the temperature and stress of the wind turbine concrete is determined, including: Determining an overall performance degree of the maximum temperature of the fan concrete based on the first correlation degree and the second correlation degree; Based on the overall performance and impact of the maximum temperature, the weight ratio of temperature and stress of the wind turbine concrete is determined.

2. The method for constructing a digital model of a fan foundation based on temperature field and stress field analysis according to claim 1, characterized in that: Determine the degree of influence of the temperature of the fan concrete on the stress of the fan concrete, including: Based on the maximum temperature and maximum stress of the fan concrete, determine the initial influence of the current temperature of the fan concrete on the stress; Determine the similarity of the trapezoidal lines based on the trapezoidal line of temperature and the trapezoidal line of stress of the fan concrete; Based on the trapezoidal line similarity, the initial influence degree is corrected to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

3. The method for constructing a digital model of a fan foundation based on temperature field and stress field analysis according to claim 2 is characterized in that: Based on the trapezoidal line similarity, the initial influence degree is corrected to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete, including: Determine the trapezoidal lines of candidate stresses whose trapezoidal line similarity is greater than the initial influence degree; Determine a number ratio based on the total number of trapezoidal lines of stress and the number of trapezoidal lines of the candidate stress; The initial influence degree is corrected based on the number ratio to obtain the influence degree of the temperature of the fan concrete on the stress of the fan concrete.

4. The method for constructing a digital model of a fan foundation based on temperature field and stress field analysis according to claim 1 is characterized in that: Based on the first correlation level and the second correlation level, the overall performance level of the maximum temperature of the fan concrete is determined, including: Fusing the first correlation levels to obtain a first fusion result; Fusing the second correlation degree with the first correlation degree to obtain a second fusion result; Based on the ratio between the first fusion result and the second fusion result, the overall performance degree of the maximum temperature of the fan concrete is obtained.

5. The method for constructing a digital model of a wind turbine foundation based on temperature field and stress field analysis according to claim 1, characterized in that: Based on the overall performance and impact of the maximum temperature, determine the weight ratio of temperature and stress of the wind turbine concrete, including: The influence degree is adjusted by using a preset adjustment value to obtain an adjusted influence degree; Based on the adjusted impact level and the overall performance level of the maximum temperature, the weighted ratio of temperature to stress of the wind turbine concrete is determined.

6. The method for constructing a digital model of a fan foundation based on temperature field and stress field analysis according to claim 1, characterized in that: Based on the weight ratio, a digital model of the fan foundation of the fan concrete is constructed, including: Obtaining an initial loss function of an initial wind turbine basic digital model; Based on the weight ratio, the initial loss function is corrected to obtain a corrected loss function; Based on the corrected loss function, the initial wind turbine basic digital model is adjusted to obtain the wind turbine basic digital model.

7. The method for constructing a digital model of a fan foundation based on temperature field and stress field analysis according to claim 6, characterized in that: Based on the weight ratio, the initial loss function is corrected to obtain the corrected loss function, including: The temperature difference information in the initial loss function is adjusted based on the weight ratio to obtain the adjusted temperature; wherein the temperature difference information is used to represent the difference between the actual temperature and the predicted temperature; Based on the difference between the weight ratio and the preset value, the stress difference information in the initial loss function is adjusted to obtain the adjusted stress; wherein the stress difference information is used to characterize the difference between the actual stress and the predicted stress; Based on the adjusted temperature and the adjusted stress, a modified loss function is determined.

Images