HSS model parameter determination method based on static sounding cone tip resistance

Abstract

The invention relates to the technical field of geotechnical engineering soil parameters, in particular to an HSS model parameter determination method based on static cone penetration cone tip resistance, which comprises the following steps: simulating a pore expansion behavior in finite element software to obtain the ultimate pressure of pore expansion; establishing the relationship between the ultimate pressure of pore expansion and the resistance of the cone tip of the static sounding; performing numerical simulation on HSS model parameters on the basis of the relationship between the ultimate pressure of pore expansion and static sounding cone tip resistance to obtain a series of HSS model parameters and corresponding static sounding cone tip resistance values, and determining the relationship between the HSS model parameters and the static sounding cone tip resistance by using a neural network model; and determining the required HSS model parameters according to the relationship between the HSS model parameters and the static sounding cone tip resistance. According to the method, the determination accuracy of the HSS model parameters is improved by establishing the relation between the HSS model parameters and the static sounding cone tip resistance.

Description

Technical Field

[0001] The invention relates to the technical field of geotechnical engineering soil parameters, and in particular to a method for determining HSS model parameters based on static penetration cone tip resistance. Background Art

[0002] In recent years, with the rapid development of infrastructure construction and the continuous advancement of urbanization in my country, the development and utilization of urban underground space has become increasingly important. Urban areas are densely populated with buildings, numerous subway pipelines, and increasingly complex environmental conditions. Major projects such as deep foundation pits and tunnels have also put forward increasingly high requirements for deformation control.

[0003] The small strain hardening constitutive model (HSS) is established on the basis of the hardening soil model (HS). It takes into account the nonlinear and stress-related characteristics of the elastic stage of the soil and has been widely used in high-precision deformation analysis of geotechnical engineering. At present, the small strain hardening constitutive model (HSS) is used as a constitutive model for numerical analysis of foundation pit excavation. Some finite element software such as Plaxis 2D / 3D and Z-Soil also set up HSS constitutive models. However, the HSS model has many parameters and is difficult to determine. At present, most regions in China have conducted little research on its applicability, and only a few regions have conducted relatively rich research on HSS model parameters. HSS model parameters usually need to be determined by physical and mechanical properties obtained from indoor geotechnical tests, but there are still some shortcomings, such as the complex loading and unloading conditions of the soil in actual engineering and the existence of soil disturbance in indoor tests. Therefore, it is necessary to conduct more research on the value of HSS model parameters.

[0004] The cone penetration test (CPT) is a commonly used in-situ test method for geotechnical engineering. It uses static pressure to uniformly press a conical probe into the soil at a certain rate to measure its penetration resistance (including cone head resistance and side wall friction or friction ratio), and divide the soil layers according to the resistance, thereby determining the engineering properties of the soil. The cone penetration test is characterized by being continuous and fast, and can overcome the shortcomings of indoor tests such as soil sample disturbance. It has become one of the most important in-situ test methods for determining the mechanical properties of soil. Therefore, establishing a widely recognized relationship between the small strain model parameters and the CPT in-situ test results has very important engineering value and practical significance for realizing the accurate and convenient determination of HSS model parameters based on the cone penetration test data. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide a method for determining HSS model parameters based on the cone tip resistance of static penetration test. The technical solution adopted is as follows:

[0006] A method for determining HSS model parameters based on static penetration cone tip resistance includes the following steps:

[0007] According to the small hole expansion theory, the small hole expansion behavior is simulated in the finite element software to obtain the limit pressure of small hole expansion;

[0008] Based on the properties of the soil in the studied area, the relationship between the limit pressure of the small hole expansion and the resistance of the static penetration cone tip is established;

[0009] Based on the relationship between the limit pressure of the small hole expansion and the cone tip resistance of the static penetration test, the HSS model parameters are modified, the cone tip resistance value is numerically simulated, and a series of HSS model parameters and corresponding cone tip resistance values ​​of the static penetration test are obtained;

[0010] According to a series of HSS model parameters and the corresponding cone tip resistance values ​​of static penetration test, the relationship between HSS model parameters and cone tip resistance of static penetration test is determined by using a neural network model.

[0011] The required HSS model parameters are determined according to the relationship between the HSS model parameters and the cone tip resistance of the static penetration test.

[0012] In combination with the first aspect above, in some possible implementations, simulating the expansion behavior of the small hole in finite element software to obtain the limit pressure of the small hole expansion includes:

[0013] A spherical small hole expansion model was established in the finite element software PLAXIS, and the HSS model was selected as the soil type. Strain was applied to the spherical small hole expansion model to make it expand, and the stress node data was selected for export. The maximum value of the average stress during the expansion process was the small hole expansion limit pressure.

[0014] In combination with the first aspect above, in some possible implementations, a relationship between the limit pressure of the small hole expansion and the resistance of the static penetration cone tip is established, including:

[0015] For clay soil, the relationship between the limiting pressure of small hole expansion and the cone tip resistance of static penetration test is established in the following way:

[0016]

[0017] Where: q c is the tip resistance of the static penetration cone; s is the limit pressure of the spherical pore expansion; s u is the undrained shear strength of the soil;

[0018] For sandy soil, the relationship between the ultimate pressure of small hole expansion and the cone tip resistance of static penetration test is established in the following way:

[0019]

[0020] Where: is the effective internal friction angle of soil.

[0021] In combination with the first aspect above, in some possible implementations, a series of HSS model parameters and corresponding static penetration cone tip resistance values ​​are obtained, including:

[0022] The benchmark HSS model parameters are determined according to the empirical relationship of the soil in the study area, and the benchmark HSS model parameters are modified up and down for numerical simulation. Based on the relationship between the limit pressure of the small hole expansion and the static penetration cone tip resistance, a series of HSS model parameters and corresponding static penetration cone tip resistance values ​​are obtained.

[0023] In combination with the first aspect above, in some possible implementations, performing an upward and downward floating modification on HSS model parameters for numerical simulation further includes:

[0024] A parameter sensitivity analysis is performed on the HSS model parameters to determine the HSS model parameters that have the greatest impact on the cone tip resistance of the static penetration test, and the changes in the numerical simulation of the HSS model parameters with the greatest impact are added.

[0025] In combination with the above-mentioned first aspect, in some possible implementations, the neural network model is an artificial neural network model.

[0026] In combination with the first aspect, in some possible implementations, the relationship between the HSS model parameters and the cone tip resistance of the static penetration test is determined using a neural network model, including:

[0027] The artificial neural network model is trained using a series of HSS model parameters and corresponding static penetration cone tip resistance values ​​to obtain an initial relationship between the HSS model parameters and the static penetration cone tip resistance; the accuracy index of the artificial neural network model during training adopts mean square error, and the random gradient descent algorithm optimized by Momentum is used for weight update;

[0028] The network structure of the trained artificial neural network model is simplified to correct the initial relationship between the HSS model parameters and the static penetration cone tip resistance, thereby finally obtaining the relationship between the HSS model parameters and the static penetration cone tip resistance.

[0029] In combination with the first aspect above, in some possible implementations, in the network structure of the artificial neural network model:

[0030] The value of a single neuron is represented as:

[0031]

[0032] Where: a is the value of the neuron; x iis the input variable; w i is the weight; m is the number of input variables;

[0033] The hyperbolic tangent function is used as the activation function to activate the value of a single neuron;

[0034] The input layer uses the HSS model parameters as the variable x and normalizes the variable x;

[0035] The hidden layer neurons can be calculated according to the following formula:

[0036]

[0037] Where: N 1 is the hidden layer neuron; tanh is the hyperbolic tangent function; W 01 and B 01 are the weight matrix and bias matrix between the input layer and the hidden layer respectively; N 0 is the variable of the input layer;

[0038] The output layer can be expressed as:

[0039]

[0040] Where: Y p,k is the predicted value of the output variable of the output layer; Y m,max and Y m,min are the maximum and minimum values ​​of the HSS model parameters, respectively. The subscript m is used to indicate that the data are measured values, and p is used to indicate that the data are predicted values. k is the number of output variables. 12 and B 12 are the weight matrix and bias matrix between the hidden layer and the output layer, respectively.

[0041] In combination with the first aspect, in some possible implementations, determining required HSS model parameters includes:

[0042] Based on the relationship between the HSS model parameters and the cone tip resistance of the static penetration test, the required HSS model parameters are determined according to the cone tip resistance value of the soil layer in the actual engineering project and some known HSS model parameters.

[0043] To solve the above technical problems, in the second aspect, the present invention also provides an HSS model parameter determination system based on the static penetration cone tip resistance, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method steps in the above first aspect or any possible implementation method of the first aspect when executing the computer program.

[0044] The present invention has the following beneficial effects: the present invention simulates the expansion behavior of the small hole in the finite element software according to the small hole expansion theory to obtain the limit pressure of the small hole expansion; based on the properties of the soil in the studied area, establishes the relationship between the limit pressure of the small hole expansion and the cone tip resistance of the static penetration test; based on the relationship between the limit pressure of the small hole expansion and the cone tip resistance of the static penetration test, numerically simulates the HSS model parameters to obtain a series of HSS model parameters and corresponding cone tip resistance values ​​of the static penetration test; according to a series of HSS model parameters and the corresponding cone tip resistance values ​​of the static penetration test, uses a neural network model to determine the relationship between the HSS model parameters and the cone tip resistance of the static penetration test; according to the relationship between the HSS model parameters and the cone tip resistance of the static penetration test, determines the required HSS model parameters. The present invention achieves the acquisition of HSS model parameters by in-situ testing by establishing the relationship between the HSS model parameters and the cone tip resistance of the static penetration test, thereby improving the accuracy of determining the HSS model parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] 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.

[0046] Figure 1 It is an overall logic block diagram of a method for determining HSS model parameters based on static penetration cone tip resistance according to an embodiment of the present invention;

[0047] Figure 2 A basic flow chart of a method for determining HSS model parameters based on the cone tip resistance of a static penetration test according to an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of an expanded grid of spherical small holes in uniform soil according to an embodiment of the present invention;

[0049] Figure 4 This is a stress distribution diagram after the small hole is expanded in an embodiment of the present invention;

[0050] Figure 5 A database obtained by numerical simulation according to an embodiment of the present invention;

[0051] Figure 6 A schematic diagram of the structure of an artificial neural network model according to an embodiment of the present invention;

[0052] Figure 7 A comparison diagram of the cone tip resistance prediction value and the simulated value of the artificial neural network model of an embodiment of the present invention;

[0053] Figure 8 It is a structural schematic diagram of a system for determining HSS model parameters based on static penetration cone tip resistance according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to clearly illustrate the technical features of the present invention, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0055] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0056] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0057] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0058] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0059] Although operations or steps are described in a specific order in the drawings in the embodiments of the present invention, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or that all the operations or steps shown must be performed to obtain the desired results. In the embodiments of the present invention, these operations or steps may be performed in series; these operations or steps may also be performed in parallel; or some of these operations or steps may be performed.

[0060] At the same time, it is understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of the relevant laws, regulations and relevant provisions. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those generally understood by technicians in the technical field of the present invention, and all parameters or indicators in the formulas involved in the present invention are normalized values ​​that eliminate the influence of dimensions.

[0061] An embodiment of the present invention provides a method for determining HSS model parameters based on the cone tip resistance of static penetration test. By establishing the relationship between the HSS model parameters and the cone tip resistance, the HSS model parameters can be obtained by in-situ testing based on the cone tip resistance of static penetration test, which provides a theoretical basis for accurately and conveniently determining the HSS model parameters according to static penetration test data in various regions.

[0062] A method for determining HSS model parameters based on the cone tip resistance of static penetration test provided by an embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

[0063] Figure 1 and Figure 2 The overall logic block diagram and basic flow chart of a method for determining HSS model parameters based on the cone tip resistance of static penetration test provided by an embodiment of the present invention are respectively shown, as shown in FIG. Figure 1 and Figure 2 As shown, the method specifically comprises the following steps:

[0064] Step S100: Based on the pore expansion theory, the pore expansion behavior is simulated in finite element software to obtain the limit pressure of the pore expansion.

[0065] According to the pore expansion theory, a spherical pore expansion model is established in the finite element software PLAXIS, and the HSS model is selected as the soil type, such as Figure 3 The figure shows the grid model of the expansion of a spherical pore in uniform soil. Strain is applied to the spherical pore to make it expand. Appropriate stress node data are selected for export. The maximum value of the average stress during the expansion process is the pore expansion limit pressure, as shown in Figure 4 Shown is the stress distribution diagram after the hole expands.

[0066] Step S200: Based on the properties of the soil in the studied area, a relationship between the limiting pressure of the small hole expansion and the cone tip resistance of the static penetration test is established.

[0067] According to the properties of the soil in the studied area, the relationship between the limit pressure of the small hole expansion and the resistance of the static penetration cone tip can be established. For example, for clay soil, the relationship between the limit pressure of the small hole expansion and the resistance of the static penetration cone tip can be established in the following way:

[0068]

[0069] Where: q c is the tip resistance of the static penetration cone; s is the limit pressure of the spherical pore expansion; s u is the undrained shear strength of the soil.

[0070] For a certain city a, according to its clay soil penetration resistance p s Undrained shear strength of soil u The empirical relationship between the two, and the specific penetration resistance p recommended in the "Technical Regulations for Static Penetration Tests" of the city's engineering construction specification s The static penetration cone resistance q c The conversion relationship between the small hole expansion limit pressure of the cohesive soil in the area of ​​city a and the cone tip resistance of static penetration test is obtained:

[0071] q c =1.056p limit +0.033 (2)

[0072] Where: p limit represents the limit pressure of the expansion of the spherical hole, that is, ψ s .

[0073] For example, for sandy soil, the relationship between the limit pressure of small hole expansion and the resistance of static penetration cone tip is established in the following way:

[0074]

[0075] Where: is the effective internal friction angle of soil.

[0076] Step S300: Based on the relationship between the limit pressure of the small hole expansion and the cone tip resistance of the static penetration test, modify the HSS model parameters, perform multiple numerical simulations on the cone tip resistance value, and obtain a series of HSS model parameters and corresponding cone tip resistance values ​​of the static penetration test.

[0077] The parameters of the benchmark HSS model are determined according to the empirical relationship of the soil in the studied area, and the parameters of the benchmark HSS model are floated up and down to different degrees within a range of 30%. In addition, the depth of the simulation can be changed to consider the influence of the effective overburden stress; parameter sensitivity analysis can be performed in advance to determine several HSS model parameters that have a greater impact on the final cone tip resistance value, such as the initial modulus of dynamic shear Tangent modulus at reference stress determined by standard consolidation test Effective internal friction angle of soil Focus on increasing the changes in these HSS model parameters. Based on the relationship between the limit pressure of small hole expansion and the static penetration cone tip resistance, a database can be obtained by modifying the model parameters in the above way and performing a large number of simulations, that is, a series of HSS model parameters and the corresponding static penetration cone tip resistance values ​​can be obtained, such as Figure 5 The database obtained by numerical simulation is shown in Figure 2. Figure 5 In the equation, phi represents the internal friction angle φ' of the soil; psi represents the dilatancy angle ψ'; gamma07 represents the shear strain γ corresponding to the shear modulus decaying to 70% of the initial shear modulus. 0.7 ; G0Ref represents the initial dynamic shear modulus K0 represents the initial static side pressure coefficient K0; Rf represents the destruction ratio R f , total_MAX_p represents the limit pressure of the small hole expansion; H represents the simulation depth; qc represents the cone tip resistance q c .

[0078] Step S400: According to a series of HSS model parameters and corresponding cone tip resistance values ​​of the static penetration test, a neural network model is used to determine the relationship between the HSS model parameters and the cone tip resistance of the static penetration test.

[0079] Using artificial neural network (ANN) to build a neural network model, also known as an artificial neural network model, such as Figure 6 Shown is a schematic diagram of the artificial neural network model structure.

[0080] By training the artificial neural network model with a series of HSS model parameters and the corresponding cone tip resistance values ​​of the static penetration test, the initial relationship between the HSS model parameters and the cone tip resistance of the static penetration test can be obtained; the network structure of the trained artificial neural network model is simplified to correct the initial relationship between the HSS model parameters and the cone tip resistance of the static penetration test, so that the relationship between the HSS model parameters and the cone tip resistance of the static penetration test can be finally obtained. The specific implementation process is as follows:

[0081] Combination Figure 6 , using the above-mentioned series of HSS model parameters and the corresponding static penetration cone tip resistance value, the constructed neural network model is trained. The accuracy index used in the training process is the mean square error:

[0082]

[0083] Where: MSE is the accuracy indicator used in the training process; y i is the calculated target value of the i-th data, y′ i is the estimated value for the i-th data point; n is the number of data points.

[0084] The Momentum-SGD algorithm is used to update the weights. The SGD algorithm only considers a single loss function to calculate the corresponding gradient in the iterative calculation:

[0085]

[0086] Where: w t+1 is the updated weight value; w t are the unupdated weights; is the gradient function of the weight; a is the learning rate. When implementing, a momentum can be defined, and then the new speed is used instead of the original gradient direction for updating, which can be expressed by the following formula:

[0087]

[0088] Where: v t+1 is the updated velocity value; v t+1 is the unupdated velocity value; β is the introduced momentum, which is generally taken as β=0.9; and Lr is the learning rate.

[0089] After the above formula (5) is optimized by Momentum, the expression is as follows:

[0090] w t+1 =w t -v t+1 (7)

[0091] A simple mathematical model of a single neuron can be viewed as a nonlinear function that transforms a set of input variables x i (i=1,…,m), converted to output variable n, which is the value of the neuron:

[0092]

[0093] Where: a is the result of the calculation input to the activation function; x i is the input variable; w i is the weight; m is the number of input variables; b is the bias. Generally speaking, the bias b is regarded as the weight w i The special case of , the value of the additional input corresponds to x0, and the original values ​​are set to +1, thus simplifying the above equation (8) to the following form:

[0094]

[0095] Then, the activation function g is used to calculate a and give the unit output N. For example, the hyperbolic tangent function tanh is selected as the activation function because its function graph passes through the origin and has a faster convergence speed. Its function formula is as follows:

[0096]

[0097] The input layer uses the HSS model parameters as the variable x, which can be expressed as N 0 , which is an n×d input matrix, n is the number of parameters and d is the number of samples. The weight and bias matrices can be represented as W k =[n k , n k-1 ] and B=[n k ,1],n k is the number of neurons in the kth hidden layer, n k-1 is the number of neurons in the k-1th hidden layer. All parameters also need to be normalized:

[0098]

[0099] Where: x′ is the normalized variable; x min and x max are the minimum and maximum values ​​of variable x respectively. The hidden layer neurons can be calculated according to the following formula:

[0100]

[0101] Where: N 1 is the hidden layer neuron; W 01 and B 01 are the weight matrix and bias matrix between the input layer and the hidden layer respectively. Meanwhile, the output layer can be expressed as:

[0102]

[0103] Where: Y p,k is the predicted value of the output variable of the output layer; Y m,max and Y m,min are the maximum and minimum values ​​of the HSS model parameters, respectively. The subscript m is used to indicate that the data are measured values, and p is used to indicate that the data are predicted values. k is the number of output variables. 12 and B 12 are the weight matrix and bias matrix between the hidden layer and the output layer, respectively.

[0104] While ensuring the prediction accuracy, the number of neurons is reduced as much as possible to simplify the structure of the artificial neural network model. The relationship between the HSS model parameters and the static penetration cone tip resistance is established using the training set, and the fitting effect is judged using the test set data. Figure 7 The figure shows a comparison between the predicted value and the simulated value of the cone tip resistance of the artificial neural network model. The appropriate input parameters are adjusted and selected until a satisfactory error is achieved, thereby obtaining an empirical formula for the HSS model parameters and the cone tip resistance, and thus establishing a relationship between the HSS model parameters and the cone tip resistance of static penetration.

[0105] Step S500: Determine the required HSS model parameters according to the relationship between the HSS model parameters and the static penetration cone tip resistance.

[0106] After establishing the relationship between the HSS model parameters and the cone tip resistance of the static penetration test, the required HSS model parameters can be quickly and accurately determined based on the cone tip resistance value of the soil layer in the actual engineering project and some known HSS model parameters.

[0107] The present invention establishes the connection between HSS model parameters and the cone tip resistance of static penetration test by carrying out numerical simulation in finite element software; introduces an artificial neural network model, makes full use of a large number of databases obtained by numerical simulation, and forms a simple and fast method for determining HSS model parameters based on the cone tip resistance of static penetration test, which can avoid the time and economic costs caused by a large number of complex geotechnical tests, and also avoids the problems of soil sample disturbance that may exist in indoor tests, and provides a theoretical basis for various regions to quickly and accurately determine HSS model parameters based on in-situ test data.

[0108] Based on the same inventive concept, the embodiment of the present invention also provides a HSS model parameter determination system based on static penetration cone tip resistance, such as Figure 8 As shown, the control system includes: a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and running on the processor 802, wherein when the processor 802 executes the computer program 803, the system can execute any of the HSS model parameter determination methods based on the static penetration cone tip resistance introduced above.

[0109] The embodiment of the present invention can divide the system into functional modules according to the above method example. For example, each functional module can be corresponded to, 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.

[0110] It should be noted that the above-described 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 scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for determining HSS model parameters based on static penetration cone tip resistance, characterized in that: The following steps are involved: According to the small hole expansion theory, the small hole expansion behavior is simulated in the finite element software, and the limit pressure of the small hole expansion is obtained; Based on the properties of the soil in the studied area, the relationship between the limit pressure of the small hole expansion and the resistance of the static penetration cone tip is established; Based on the relationship between the limit pressure of the small hole expansion and the cone tip resistance of the static penetration test, the HSS model parameters are modified, the cone tip resistance value is numerically simulated, and a series of HSS model parameters and corresponding cone tip resistance values ​​of the static penetration test are obtained; According to a series of HSS model parameters and the corresponding cone tip resistance values ​​of static penetration test, the relationship between HSS model parameters and cone tip resistance of static penetration test is determined by using a neural network model. The required HSS model parameters are determined according to the relationship between the HSS model parameters and the cone tip resistance of the static penetration test.

2. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 1 is characterized in that: The expansion behavior of the small hole is simulated in the finite element software, and the limit pressure of the small hole expansion is obtained, including: A spherical small hole expansion model was established in the finite element software PLAXIS, and the HSS model was selected as the soil type. Strain was applied to the spherical small hole expansion model to make it expand, and the stress node data was selected for export. The maximum value of the average stress during the expansion process was the small hole expansion limit pressure.

3. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 1 is characterized in that: Establish the relationship between the limit pressure of small hole expansion and the resistance of static penetration cone tip, including: For clay soil, the relationship between the limiting pressure of small hole expansion and the cone tip resistance of static penetration test is established in the following way: Where: q c is the tip resistance of the static penetration cone; s is the limit pressure of the spherical pore expansion; s u is the undrained shear strength of the soil; For sandy soil, the relationship between the ultimate pressure of small hole expansion and the cone tip resistance of static penetration test is established in the following way: Where: is the effective internal friction angle of soil.

4. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 1 is characterized in that: Obtain a series of HSS model parameters and the corresponding static penetration cone tip resistance values, including: The benchmark HSS model parameters are determined according to the empirical relationship of the soil in the study area, and the benchmark HSS model parameters are modified up and down for numerical simulation. Based on the relationship between the limit pressure of the small hole expansion and the static penetration cone tip resistance, a series of HSS model parameters and corresponding static penetration cone tip resistance values ​​are obtained.

5. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 4 is characterized in that: Modifying the HSS model parameters up and down for numerical simulation also includes: A parameter sensitivity analysis is performed on the HSS model parameters to determine the HSS model parameters that have the greatest impact on the cone tip resistance of the static penetration test, and the changes in the numerical simulation of the HSS model parameters with the greatest impact are added.

6. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 1 is characterized in that: The neural network model is an artificial neural network model.

7. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 6 is characterized in that: The neural network model is used to determine the relationship between the HSS model parameters and the cone tip resistance of the static penetration test, including: The artificial neural network model is trained using a series of HSS model parameters and corresponding static penetration cone tip resistance values ​​to obtain an initial relationship between the HSS model parameters and the static penetration cone tip resistance; the accuracy index of the artificial neural network model during training adopts mean square error, and the random gradient descent algorithm optimized by Momentum is used for weight update; The network structure of the trained artificial neural network model is simplified to correct the initial relationship between the HSS model parameters and the cone tip resistance of the static penetration test, so as to finally obtain the relationship between the HSS model parameters and the cone tip resistance of the static penetration test.

8. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 7 is characterized in that: In the network structure of the artificial neural network model: The value of a single neuron is represented as: Where: a is the value of the neuron; x i is the input variable; w i is the weight; m is the number of input variables; The hyperbolic tangent function is used as the activation function to activate the value of a single neuron; The input layer uses the HSS model parameters as the variable x and normalizes the variable x; The hidden layer neurons can be calculated according to the following formula: Where: N 1 are the hidden layer neurons; tanh is the hyperbolic tangent function; W 01 and B 01 are the weight matrix and bias matrix between the input layer and the hidden layer respectively; N 0 is the variable of the input layer; The output layer can be expressed as: Where: Y p,k is the predicted value of the output variable of the output layer; Y m,max and Y m,min are the maximum and minimum values ​​of the HSS model parameters, respectively. The subscript m is used to indicate that the data are measured values, and p is used to indicate that the data are predicted values. k is the number of output variables. W 12 and B 12 are the weight matrix and bias matrix between the hidden layer and the output layer, respectively.

9. The method for determining HSS model parameters based on the cone tip resistance of static penetration test according to claim 1 is characterized in that: Determine the required HSS model parameters, including: Based on the relationship between the HSS model parameters and the cone tip resistance of the static penetration test, the required HSS model parameters are determined according to the cone tip resistance value of the soil layer in the actual engineering project and some known HSS model parameters.

Images