Method and device for predicting bearing capacity of screw pile in marine facies soft soil area

By using finite element numerical simulation and model training, a prediction model for the bearing capacity of helical piles was established, which solved the problems of high cost and low accuracy in predicting the bearing capacity of helical piles in marine soft soil areas, and achieved efficient and accurate prediction results.

CN118940431AActive Publication Date: 2024-11-12JIANGSU OCEAN UNIV
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410978328.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

Existing technologies rely on empirical formulas and field tests to predict the bearing capacity of helical piles in marine soft soil areas, resulting in high costs and low prediction accuracy. It is also difficult to quantify the influence of parameters such as soil type, density, and shear strength.

Method used

The finite element method is used to model soil and pile variables. Key variables are obtained through simulation, dimensionality reduction and model training are performed to establish a prediction model for the bearing capacity of helical piles. The trained model is then used for prediction.

Benefits of technology

It reduces the cost of predicting the bearing capacity of helical piles, while improving the accuracy of the prediction and reducing the reliance on field tests.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940431A_ABST
    Figure CN118940431A_ABST
Patent Text Reader

Abstract

The invention provides a spiral pile bearing capacity prediction method and device for a marine facies soft soil area, relates to the technical field of foundation engineering, and aims at improving the prediction accuracy of the spiral pile bearing capacity while reducing the spiral pile bearing capacity prediction cost. The method comprises the steps of obtaining a soil mass variable of a marine facies soft soil area and a pile body variable of a screw pile; carrying out analog simulation to obtain the screw pile bearing capacities corresponding to the soil body variables and the pile body variables under the condition of different values; dimension reduction is carried out on the soil body variables and the pile body variables to obtain key soil body variables and key pile body variables; performing model training by taking different values of the key soil body variable and the key pile body variable and the screw pile bearing capacities corresponding to the different values as sample data to obtain a screw pile bearing capacity prediction model; and predicting the bearing capacity of the screw pile through the trained screw pile bearing capacity prediction model.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of foundation engineering, and in particular to a method and device for predicting the bearing capacity of screw piles in marine soft soil areas. Background Art

[0002] Marine soft soil is widely distributed in the southeastern coastal areas of my country. It has problems such as high water content and poor physical properties. The foundation structures built on it often face problems such as low bearing capacity and uneven settlement, which brings huge challenges to the construction of foundation projects in coastal areas. As a kind of heterogeneous pile, the spiral pile is composed of one or more spiral plates welded on a round or square long screw or steel rod with equal or unequal spacing. A certain torque is applied to the top of the screw by mechanical means to make it screw into the soil layer. It is an anchoring structure that utilizes the resistance of deep soil. Due to its advantages such as easy installation, low pollution and high economic benefits, it is widely used in power grids, photovoltaic power stations, ports and other projects in marine soft soil areas. However, there are also some problems with spiral piles. In soft clay, the disturbance caused by the installation to the surrounding soil makes the bearing capacity insufficient. Increasing the length of the spiral pile will lead to a larger slenderness ratio, thereby reducing the stability of the pile body.

[0003] Traditional predictions of the bearing capacity of spiral piles often rely on empirical formulas and field tests. However, in actual engineering, soil type, density, shear strength, pile size and shape and other parameters that are difficult to quantify will affect the bearing capacity of the pile. In the past few decades, scholars have proposed many methods to evaluate and predict the bearing capacity of spiral piles. However, the most direct and reliable method is still static loading until the pile fails. Although there are innovative methods such as high-strain dynamic testing based on one-dimensional wave propagation theory and advanced pile drive analyzers, they have not been widely used due to factors such as high test costs. Summary of the invention

[0004] The embodiments of the present application provide a method and system for predicting the bearing capacity of a screw pile in a marine soft soil area, which are used to improve the prediction accuracy of the bearing capacity of the screw pile while reducing the prediction cost of the bearing capacity of the screw pile.

[0005] An embodiment of the present invention provides a method for predicting the bearing capacity of a screw pile in a marine soft soil area, the method comprising:

[0006] Obtain soil variables in marine soft soil areas and pile variables of screw piles;

[0007] The soil variables and the pile variables are modeled by a finite element numerical simulation method, and the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​are obtained by simulation;

[0008] According to different values ​​of the soil variables and the pile variables obtained by simulation and their corresponding screw pile bearing capacities under different values, the soil variables and the pile variables are respectively reduced in dimension to obtain key soil variables and key pile variables;

[0009] The different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under the different values ​​are used as sample data for model training to obtain a screw pile bearing capacity prediction model;

[0010] The bearing capacity of the screw pile is predicted by the trained screw pile bearing capacity prediction model.

[0011] In an optional embodiment provided by the present invention, the different values ​​of the soil variables and the pile variables obtained by simulation and the corresponding screw pile bearing capacities under different values ​​are respectively reduced in dimension to obtain key soil variables and key pile variables, including:

[0012] The values ​​of all variables in the key soil variables and the key pile variables obtained by simulation are input into the feature screening model to obtain the contribution value of each variable in the key soil variables and the key pile variables in obtaining the corresponding screw pile bearing;

[0013] Based on the contribution value of each variable in the soil variables and the pile variables, key soil variables and key pile variables are determined.

[0014] In an optional embodiment provided by the present invention, the key soil variables include at least: cement soil strength and soil strength; the key pile variables include at least: spiral blade diameter, pile diameter, number of spiral blades and spiral blade spacing.

[0015] In an optional embodiment provided by the present invention, before the simulation obtains the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values, the method further includes:

[0016] Determining a first load-displacement curve based on the relationship between displacement and load in the simulation;

[0017] Compare the second load-displacement curve of the on-site compression test with the first load-displacement curve;

[0018] If the numerical deviation between the curve comparison results is less than a preset numerical value, the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​are obtained through simulation.

[0019] In an optional embodiment provided by the present invention, before the simulation obtains the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values, the method further includes:

[0020] If the numerical deviation between the curve comparison results is less than a preset value, the bearing capacities corresponding to the second load-displacement curve and the first load-displacement curve are determined by the bitangent method;

[0021] If the bearing capacity difference between the second load-displacement curve and the first load-displacement curve is smaller than a target value, the screw pile bearing capacities corresponding to the soil variables and the pile variables with different values ​​are obtained through simulation.

[0022] In an optional embodiment provided by the present invention, the screw pile bearing capacity prediction model includes: an input layer, a hidden layer and an output layer; the number of nodes in the input layer is the number of input variables after dimensionality reduction.

[0023] In an optional embodiment provided by the present invention, the different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​are used as sample data for model training to obtain a screw pile bearing capacity prediction model, including:

[0024] Arrange and combine the number of hidden layers and the number of neurons contained in the hidden layers to obtain multiple initial network models; and train each initial network model according to the sample data;

[0025] Calculate the mean square error of each trained initial network model;

[0026] The initial network model with the smallest average error is used as the bearing capacity prediction model of the screw pile.

[0027] In an optional embodiment provided by the present invention, before using the key soil variables, different values ​​of the key pile variables and the screw pile bearing capacities corresponding to the different values ​​as sample data for model training to obtain the screw pile bearing capacity prediction model, the method further includes:

[0028] Outlier filtering and normalization are performed on the key soil variables and the key pile variables.

[0029] An embodiment of the present invention provides a screw pile bearing capacity prediction device for marine soft soil areas, the device comprising:

[0030] An acquisition module is used to obtain soil variables in marine soft soil areas and pile variables of screw piles;

[0031] A simulation module, used for modeling the soil variables and the pile variables by using a finite element numerical simulation method, and simulating and obtaining the corresponding screw pile bearing capacities of the soil variables and the pile variables under different values;

[0032] A dimension reduction module is used to reduce the dimensions of the soil variables and the pile variables respectively to obtain key soil variables and key pile variables according to different values ​​of the soil variables and the pile variables obtained by simulation and the corresponding screw pile bearing capacities under different values;

[0033] A training module, for using different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​as sample data for model training to obtain a screw pile bearing capacity prediction model;

[0034] The prediction module is used to predict the bearing capacity of the screw pile by using the trained screw pile bearing capacity prediction model.

[0035] The present invention provides a method and device for predicting the bearing capacity of spiral piles in marine soft soil areas. First, soil variables and pile body variables of spiral piles in marine soft soil areas are obtained. Then, a finite element numerical simulation method is used to model the soil variables and pile body variables. The spiral pile bearing capacities corresponding to the soil variables and pile body variables under different values ​​are obtained by simulation. According to different values ​​of key soil variables and key pile body variables obtained by simulation and their corresponding spiral pile bearing capacities under different values, soil variables and pile body variables are respectively reduced in dimension to obtain key soil variables and key pile body variables. Different values ​​of key soil variables and key pile body variables and their corresponding spiral pile bearing capacities under different values ​​are used as sample data for model training to obtain a spiral pile bearing capacity prediction model. Finally, the spiral pile bearing capacity is predicted by the trained spiral pile bearing capacity prediction model. Compared with traditional spiral pile bearing capacity predictions which often rely on empirical formulas and field tests, the present application obtains the sample data required for training the spiral pile bearing capacity prediction model through simulation, and then trains the spiral pile bearing capacity prediction model based on the sample data, so as to predict the spiral pile bearing capacity based on the trained spiral pile bearing capacity prediction model. Thus, the present application can reduce the cost of spiral pile bearing capacity prediction while improving the prediction accuracy of spiral pile bearing capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a method for predicting the bearing capacity of screw piles in marine soft soil areas provided in this application;

[0037] Figure 2 A structural diagram of a spiral pile core rigid composite pile provided in this application;

[0038] Figure 3 A network structure diagram of a screw pile bearing capacity prediction model provided in this application;

[0039] Figure 4 A schematic structural diagram of a screw pile bearing capacity prediction device for marine soft soil areas provided in this application. DETAILED DESCRIPTION

[0040] In order to better understand the above-mentioned technical scheme, the technical scheme of the embodiments of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the embodiments of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments may be combined with each other.

[0041] like Figure 1 As shown, this embodiment provides a method for predicting the bearing capacity of screw piles in marine soft soil areas. The execution steps of the method are:

[0042] S101, obtaining soil variables in the marine soft soil area and pile variables of the screw pile.

[0043] like Figure 2 As shown, the spiral pile in this embodiment can be a spiral core rigid composite pile (Helix Stiffened Cement Mixed Pile, HSCMP), also known as a grouting spiral pile, a pressure grouting spiral pile, a cement soil spiral pile, etc. The spiral blades enhance the interaction between the spiral pile core and the cement soil, so that the bearing capacity of the pile foundation can be fully exerted.

[0044] In this embodiment, a parameter sample of the HSCM pile compressive bearing capacity variable in the marine soft soil area is established according to the full-scale test method of the field test, that is, the soil variables in the marine soft soil area and the pile variables of the spiral pile are obtained. The soil variables are soil quality related data corresponding to the marine soft soil area, such as soil variables can include: gravity, moisture content, compression modulus, ultimate lateral resistance, ultimate end resistance, cement soil strength and soil strength; the pile variables are related attribute data of the spiral pile used, such as pile variables can include: pile stiffness, pile body length, spiral blade diameter, pile diameter, number of spiral blades and spiral blade spacing and other related parameters. This embodiment does not specifically limit the pile and soil variables. Among them, after the on-site soil variables are extracted, they can be shown in Table 1 as follows:

[0045] Table 1

[0046]

[0047] S102, using a finite element numerical simulation method to model the soil variables and the pile variables, and simulating to obtain the corresponding screw pile bearing capacities of the soil variables and the pile variables under different values.

[0048] Specifically, this embodiment uses the finite element numerical simulation method to model soil variables and pile variables. The soil around the pile can be based on the Mohr-Coulomb constitutive model and the soil hardening constitutive model. The contact surface is divided into steel pipe-cement soil contact surface and pile-soil contact surface according to the different contact materials. Linear elastic non-porous materials are used to construct cement soil, and the pile body is based on the elastoplastic theory.

[0049] Among them, the soil variables and pile variables are manually adjusted and set according to needs or actual conditions at different values, that is, the corresponding screw pile bearing capacity under simulation is set at different values ​​of the soil variables and pile variables.

[0050] S103, according to different values ​​of the soil variables and the pile variables obtained by simulation and their corresponding screw pile bearing capacities under different values, respectively reduce the dimensions of the soil variables and the pile variables to obtain key soil variables and key pile variables.

[0051] Among them, the key soil variables are the soil variables that have a greater impact on the bearing capacity of the spiral pile, and the key pile variables are the pile variables that have a greater impact on the bearing capacity of the spiral pile.

[0052] In an optional embodiment provided by the present application, according to the different values ​​of the soil variables and the pile variables obtained by simulation and the corresponding spiral pile bearing capacities under different values, the soil variables and the pile variables are respectively reduced in dimension to obtain key soil variables and key pile variables, including: inputting the values ​​of all variables in the key soil variables and the key pile variables obtained by simulation into the feature screening model to obtain the contribution value of each variable in the key soil variables and the key pile variables in obtaining the corresponding spiral pile bearing capacity; determining the key soil variables and the key pile variables based on the contribution value of each variable in the soil variables and the pile variables. Among them, the feature screening model is a model for screening key variables, which can be a general neural network model. In this embodiment, a small amount of sample data can be input into the model, and then the key soil variables in the soil variables and the key pile variables in the pile variables are determined by the model.

[0053] Specifically, in this embodiment, the formula y i =y base +f(x i1 )+f(x i2 )+f(x i3 )+...+f(xij ) represents the contribution value of each sample feature in the sample data to the sample label in the feature screening model. ij is the jth feature in the i-th sample data; y i is the sample label (target value) of the i-th sample data; y base It is the baseline of the entire data set, usually the mean of the target parameters of all samples. In the application, it is the mean of the ultimate compressive bearing capacity of all samples. ij ) is the jth feature in the i-th sample data for the target value y i contribution value.

[0054] In this embodiment, after reducing the dimension of soil variables and pile variables by the above method, the key soil variables obtained include at least: cement soil strength and soil strength; the key pile variables include at least: spiral blade diameter, pile diameter, number of spiral blades and spiral blade spacing.

[0055] Furthermore, in order to ensure the accuracy of the spiral pile bearing capacity obtained through simulation, the present embodiment also needs to verify the results of the simulation. That is, before obtaining the spiral pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​through simulation, it is necessary to determine the first load-displacement curve through the relationship between displacement and load in the simulation; compare the second load-displacement curve of the field compression test with the first load-displacement curve; if the numerical deviation between the curve comparison results is less than the preset value, the simulation obtains the spiral pile bearing capacities corresponding to the soil variables and the pile variables under different values. The horizontal axis in the load-displacement curve is the bearing capacity, and the vertical axis is the displacement.

[0056] To further verify the accuracy of the simulation results, before simulating and obtaining the spiral pile bearing capacities corresponding to the soil variables and the pile variables under different values, the method of this embodiment also includes: if the numerical deviation between the curve comparison results is less than the preset value, the bearing capacities corresponding to the second load-displacement curve and the first load-displacement curve are determined by the double tangent method; if the bearing capacity difference between the second load-displacement curve and the first load-displacement curve is less than the target value, the spiral pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​are obtained by simulation. Among them, the preset value and the target value are values ​​set according to actual needs, and this embodiment does not make specific restrictions on this.

[0057] It should be noted that the double tangent method is to take the intersection of the two tangents of the flat part and the end part of the curve on the first load-displacement curve and the second load-displacement curve, and then compare the bearing capacities of the two intersections. If the difference in the bearing capacities of the two intersections is less than the target value, the simulation obtains the corresponding spiral pile bearing capacities of the soil variables and the pile variables under different values. For example, the ultimate bearing capacity of the curve is determined by the double tangent method. The ultimate bearing capacity and displacement of the first load-displacement curve are 504.19KN and 22.7mm, and the second load-displacement curve is 494.17KN and 21.4mm, and the ultimate bearing capacity deviation is 2.03%. The above results show that the simulation model can better simulate the actual deformation of HSCM piles under downward pressure in restored soft soil.

[0058] S104, using different values ​​of the key soil variables and the key pile variables and their corresponding screw pile bearing capacities under different values ​​as sample data for model training to obtain a screw pile bearing capacity prediction model.

[0059] In this embodiment, before using the different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​as sample data for model training to obtain the screw pile bearing capacity prediction model, the method further includes: filtering outliers and normalizing the key soil variables and the key pile variables. For example, in this embodiment, normalization can be performed using the following formula:

[0060]

[0061] Among them, X represents the original data, X min and X max Represent the minimum and maximum values ​​in the sample data set respectively. Through this conversion method, it is ensured that all eigenvalues ​​will be in the interval of 0 and 1, thereby eliminating the influence of dimension and unifying the data scale.

[0062] It should be noted that the spiral pile bearing capacity prediction model in this embodiment includes: an input layer, a hidden layer and an output layer; the number of nodes in the input layer is the number of input variables after the dimension is reduced. The training process of the spiral pile bearing capacity prediction model is: based on the number of hidden layers and the number of neurons contained in the hidden layers, multiple initial network models are obtained by permutation and combination; and each initial network model is trained according to the sample data; the mean square error of each trained initial network model is calculated; and the initial network model with the smallest average error is used as the spiral pile bearing capacity prediction model. For example, the hidden layer contains up to 3 layers, and the number of neurons contained in each hidden layer is 5-10. Then, these data can be permuted and combined, and then each initial network model is trained according to the sample data; the mean square error of each trained initial network model is calculated; and the initial network model with the smallest average error is used as the spiral pile bearing capacity prediction model. For example, through comparison, it is found that the mean square error of the initial network model with three hidden layers and 10 neurons in each hidden layer is the smallest, so the network structure of the initial network model is used as the network structure of the screw pile bearing capacity prediction model.

[0063] For example, this embodiment can use a small amount of sample data to train multiple initial network models, and then select one of the multiple trained initial network models as a spiral pile bearing capacity prediction model. Each group is composed of input parameters (sample data, that is, the numerical values ​​corresponding to key soil variables and key pile variables, respectively) and output parameters (sample labels corresponding to the sample data, that is, the spiral pile bearing capacity obtained through simulation). The sample data can specifically include blade spacing, number of blades, cement soil strength, soil strength, pile diameter, spiral blade diameter, etc.

[0064] After the network structure of the screw pile bearing capacity prediction model, this embodiment continues to train the screw pile bearing capacity prediction model through other sample data until the number of iterations reaches the maximum value or the error is within the preset error range, and the model training is completed. The error can be determined by the mean square error MSE and correlation.

[0065] like Figure 3 FIG. 1 is a network structure diagram of a screw pile bearing capacity prediction model provided by this embodiment. The calculation process of each neuron in the hidden layer of the screw pile bearing capacity prediction model is as follows:

[0066]

[0067] y j =Φ(h j )=Φ(w yj h j +b j2 );

[0068] Where n is the number of input variables, i.e. the total number of key soil variables and key pile variables, and w ij is the weight of the i-th variable in the j-th neuron, x i is the i-th variable of the input, such as x1 represents the number of spiral blades, x2 represents the spiral blade spacing; b j1 is the threshold between the input layer and the first hidden layer, f is the activation function, Φ is the linear function, w yj is the weight between the jth neuron and the output variable y, b j2 is the threshold between the first hidden layer and the second hidden layer. The prediction model for the bearing capacity of the screw pile in this embodiment regards the input variables as nodes. For example, there are 6 input variables in this application, that is, 6 nodes. The codes of these nodes are i, x, and i The value is the specific value (for example, input node 1, the corresponding x1 value is 5). Similarly, j represents the neurons in the next layer, that is, the first hidden layer.

[0069] For example, the neural network structure of the prediction model for the bearing capacity of screw piles in this embodiment is: input layer - first hidden layer - second hidden layer - third hidden layer - fourth hidden layer - output layer. The input layer includes six nodes, and each of the four hidden layers contains 10 neurons. The output layer has only one node, namely the bearing capacity of screw piles. In this embodiment, there is a threshold between each hidden layer, b j1 refers to the threshold between the input layer and the first hidden layer, b j2 Refers to the threshold between the first hidden layer and the second hidden layer. The threshold is a concept in neural networks and can be simply understood as a bias. A value multiplied by the weight plus the bias is the final output value of the neuron. This value is then told to the next hidden layer neuron, and the next neuron undergoes the same calculation, and so on, and finally the final output parameter is obtained.

[0070] Taking the input layer and the first hidden layer as an example, the nodes in the input layer tell the values ​​of the input variables to the neurons in the hidden layer. The neuron coded j needs to perform three operations, namely sum, activation, and mapping. The sum is the first formula Activation is the second formula The mapping is the third formula y j =Φ(h j )=Φ(w yj h j +b j2 ). Then this neuron transforms the mapped y j Tell the next hidden layer, and the neurons in the next hidden layer perform the same operation, and so on, and finally get the output parameter, that is, the compressive bearing capacity

[0071] S105, predicting the bearing capacity of the screw pile using the trained screw pile bearing capacity prediction model.

[0072] Specifically, after training the spiral pile bearing capacity prediction model, this embodiment can extract the pile body variables of the spiral pile to be tested and the soil body variables of the marine soft soil area where it is located to obtain key pile body variables and key soil body variables, and then input the key pile body variables and key soil body variables into the spiral pile bearing capacity prediction model to obtain the spiral pile bearing capacity of the spiral pile to be tested.

[0073] The embodiment of the present application provides a method for predicting the bearing capacity of spiral piles in marine soft soil areas. First, soil variables in the marine soft soil area and pile variables of the spiral piles are obtained. Then, the soil variables and pile variables are modeled using a finite element numerical simulation method. The spiral pile bearing capacities corresponding to the soil variables and pile variables under different values ​​are obtained by simulation. According to different values ​​of key soil variables and key pile variables obtained by simulation and their corresponding spiral pile bearing capacities under different values, the soil variables and pile variables are respectively reduced in dimension to obtain key soil variables and key pile variables. Different values ​​of key soil variables and key pile variables and their corresponding spiral pile bearing capacities under different values ​​are used as sample data for model training to obtain a spiral pile bearing capacity prediction model. Finally, the spiral pile bearing capacity is predicted by the trained spiral pile bearing capacity prediction model. Compared with traditional spiral pile bearing capacity predictions which often rely on empirical formulas and field tests, the present application obtains the sample data required for training the spiral pile bearing capacity prediction model through simulation, and then trains the spiral pile bearing capacity prediction model based on the sample data, so as to predict the spiral pile bearing capacity based on the trained spiral pile bearing capacity prediction model. Thus, the present application can reduce the cost of spiral pile bearing capacity prediction while improving the prediction accuracy of spiral pile bearing capacity.

[0074] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0075] In one embodiment, a screw pile bearing capacity prediction device for marine soft soil areas is provided, and the screw pile bearing capacity prediction device for marine soft soil areas corresponds to the screw pile bearing capacity prediction method for marine soft soil areas in the above embodiment. Figure 4 As shown in the figure, the functional modules of the screw pile bearing capacity prediction device for marine soft soil areas are described in detail as follows:

[0076] An acquisition module 41 is used to acquire soil variables in marine soft soil areas and pile variables of screw piles;

[0077] A simulation module 42 is used to model the soil variables and the pile variables using a finite element numerical simulation method, and simulate and obtain the corresponding screw pile bearing capacities of the soil variables and the pile variables under different values;

[0078] A dimension reduction module 43 is used to reduce the dimensions of the soil variables and the pile variables to obtain key soil variables and key pile variables according to different values ​​of the soil variables and the pile variables obtained by simulation and the corresponding screw pile bearing capacities under different values;

[0079] A training module 44 is used to use different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​as sample data to perform model training to obtain a screw pile bearing capacity prediction model;

[0080] The prediction module 45 is used to predict the bearing capacity of the screw pile by using the trained screw pile bearing capacity prediction model.

[0081] In an optional embodiment provided by the present invention, the dimension reduction module 43 is specifically used for:

[0082] The values ​​of all variables in the key soil variables and the key pile variables obtained by simulation are input into the feature screening model to obtain the contribution value of each variable in the key soil variables and the key pile variables in obtaining the corresponding screw pile bearing;

[0083] Based on the contribution value of each variable in the soil variables and the pile variables, key soil variables and key pile variables are determined.

[0084] In an optional embodiment provided by the present invention, the key soil variables include at least: cement soil strength and soil strength; the key pile variables include at least: spiral blade diameter, pile diameter, number of spiral blades and spiral blade spacing.

[0085] In an optional embodiment provided by the present invention, the simulation module 42 is specifically used for:

[0086] Determining a first load-displacement curve based on the relationship between displacement and load in the simulation;

[0087] Compare the second load-displacement curve of the on-site compression test with the first load-displacement curve;

[0088] If the numerical deviation between the curve comparison results is less than a preset numerical value, the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​are obtained through simulation.

[0089] In an optional embodiment provided by the present invention, the simulation module 42 is specifically used for:

[0090] If the numerical deviation between the curve comparison results is less than a preset value, the bearing capacities corresponding to the second load-displacement curve and the first load-displacement curve are determined by the bitangent method;

[0091] If the bearing capacity difference between the second load-displacement curve and the first load-displacement curve is smaller than a target value, the screw pile bearing capacities corresponding to the soil variables and the pile variables with different values ​​are obtained through simulation.

[0092] In an optional embodiment provided by the present invention, the screw pile bearing capacity prediction model includes: an input layer, a hidden layer and an output layer; the number of nodes in the input layer is the number of input variables after dimensionality reduction.

[0093] In an optional embodiment provided by the present invention, the training module 44 is specifically used for:

[0094] Arrange and combine the number of hidden layers and the number of neurons contained in the hidden layers to obtain multiple initial network models; and train each initial network model according to the sample data;

[0095] Calculate the mean square error of each trained initial network model;

[0096] The initial network model with the smallest average error is used as the bearing capacity prediction model of the screw pile.

[0097] In an optional embodiment provided by the present invention, the calculation process of each neuron in the hidden layer is:

[0098]

[0099] y=Φ(h j )=Φ(w yj h j +b j2 );

[0100] Where n is the number of input variables, w ij is the weight of the i-th variable in the j-th neuron, x i is the i-th variable of the input, b j1 is the threshold between the input layer and the first hidden layer, f is the activation function, Φ is the linear function, w yj is the weight between the jth neuron and the output variable y, b j2 is the threshold between the first hidden layer and the second hidden layer.

[0101] In an optional embodiment provided by the present invention, before using the key soil variables, different values ​​of the key pile variables and the screw pile bearing capacities corresponding to the different values ​​as sample data for model training to obtain the screw pile bearing capacity prediction model, the method further includes:

[0102] Outlier filtering and normalization are performed on the key soil variables and the key pile variables.

[0103] The specific definition of the screw pile bearing capacity prediction device for marine soft soil areas can be found in the definition of the screw pile bearing capacity prediction method for marine soft soil areas mentioned above, which will not be repeated here. Each module in the above-mentioned device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0104] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0105] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for predicting the bearing capacity of screw piles in marine soft soil areas, characterized in that: The method comprises: Obtain soil variables in marine soft soil areas and pile variables of screw piles; The soil variables and the pile variables are modeled by a finite element numerical simulation method, and the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​are obtained by simulation; According to different values ​​of the soil variables and the pile variables obtained by simulation and their corresponding screw pile bearing capacities under different values, the soil variables and the pile variables are respectively reduced in dimension to obtain key soil variables and key pile variables; The different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under the different values ​​are used as sample data for model training to obtain a screw pile bearing capacity prediction model; The bearing capacity of the screw pile is predicted by the trained screw pile bearing capacity prediction model.

2. The method according to claim 1, characterized in that According to the different values ​​of the soil variables and the pile variables obtained by simulation and their corresponding screw pile bearing capacities under different values, the soil variables and the pile variables are respectively reduced in dimension to obtain key soil variables and key pile variables, including: The values ​​of all variables in the key soil variables and the key pile variables obtained by simulation are input into the feature screening model to obtain the contribution value of each variable in the key soil variables and the key pile variables in obtaining the corresponding screw pile bearing; Based on the contribution value of each variable in the soil variables and the pile variables, key soil variables and key pile variables are determined.

3. The method according to claim 2, characterized in that The key soil variables include at least cement soil strength and soil strength; the key pile variables include at least spiral blade diameter, pile diameter, spiral blade number and spiral blade spacing.

4. The method according to claim 1, characterized in that: Before the simulation obtains the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values, the method further includes: Determining a first load-displacement curve based on the relationship between displacement and load in the simulation; Compare the second load-displacement curve of the on-site compression test with the first load-displacement curve; If the numerical deviation between the curve comparison results is less than a preset numerical value, the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values ​​are obtained through simulation.

5. The method according to claim 1, characterized in that Before the simulation obtains the screw pile bearing capacities corresponding to the soil variables and the pile variables under different values, the method further includes: If the numerical deviation between the curve comparison results is less than a preset value, the bearing capacities corresponding to the second load-displacement curve and the first load-displacement curve are determined by the bitangent method; If the bearing capacity difference between the second load-displacement curve and the first load-displacement curve is smaller than a target value, the screw pile bearing capacities corresponding to the soil variables and the pile variables with different values ​​are obtained through simulation.

6. The method according to any one of claims 1 to 5, characterized in that: The screw pile bearing capacity prediction model comprises: an input layer, a hidden layer and an output layer; the number of nodes in the input layer is the number of input variables after the dimension is reduced.

7. The method according to claim 6, characterized in that The method of using different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​as sample data for model training to obtain a screw pile bearing capacity prediction model includes: Arrange and combine the number of hidden layers and the number of neurons contained in the hidden layers to obtain multiple initial network models; and train each initial network model according to the sample data; Calculate the mean square error of each trained initial network model; The initial network model with the smallest average error is used as the bearing capacity prediction model of the screw pile.

8. The method according to claim 6, characterized in that Before obtaining a prediction model for the bearing capacity of a screw pile, the method further includes: using different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​as sample data for model training. Outlier filtering and normalization are performed on the key soil variables and the key pile variables.

9. A device for predicting the bearing capacity of screw piles in marine soft soil areas, characterized in that: The device comprises: The acquisition module is used to obtain soil variables in marine soft soil areas and pile variables of screw piles; A simulation module, used for modeling the soil variables and the pile variables by using a finite element numerical simulation method, and simulating and obtaining the corresponding screw pile bearing capacities of the soil variables and the pile variables under different values; A dimension reduction module is used to reduce the dimensions of the soil variables and the pile variables respectively to obtain key soil variables and key pile variables according to different values ​​of the soil variables and the pile variables obtained by simulation and the corresponding screw pile bearing capacities under different values; A training module, for using different values ​​of the key soil variables and the key pile variables and the corresponding screw pile bearing capacities under different values ​​as sample data for model training to obtain a screw pile bearing capacity prediction model; The prediction module is used to predict the bearing capacity of the screw pile by using the trained screw pile bearing capacity prediction model.

Citation Information

Patent Citations

  • Pile-soil interaction prediction analysis method based on machine learning

    CN111209708A

  • Pile foundation horizontal bearing capacity prediction method based on BAS-BP

    CN112926117A

  • Model error evaluation method, device and equipment for offshore wind power single pile p-y curve method

    CN116611283A

  • Method and device for predicting vertical bearing capacity of tubular pile and electronic equipment

    CN117217091A

  • Resource Allocation Based on Available Predictions

    US20150006433A1