Intelligent prediction method for mechanical behaviors in buried pipeline construction process

Abstract

The invention provides a buried pipeline construction process mechanical behavior intelligent prediction method, and belongs to the technical field of water conservancy and hydropower engineering. According to the method, geometric parameters, unit types and material parameters of a refined numerical simulation model are defined, a three-dimensional finite element model is established, the contact relation between a steel pipe and backfill soil and the contact relation between the backfill soil and undisturbed soil are established, and multi-stage load step simulation is conducted so as to simulate the actual construction process. The method comprises the following steps: acquiring test data by utilizing an orthogonal test method, and constructing an intelligent prediction model by combining a Python platform and adopting support vector regression and a genetic algorithm, thereby accurately predicting mechanical behaviors in a construction process. According to the intelligent prediction method for the mechanical behaviors in the buried pipeline construction process, the construction environment can be accurately simulated, the construction scheme can be optimized, the construction quality can be improved, the construction risk can be reduced, and remarkable technical advantages and application value are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of water conservancy and hydropower engineering, and in particular to an intelligent prediction method for mechanical behavior during a buried pipeline construction process. Background Art

[0002] Pipeline is the fifth largest means of transportation after road, rail, water and aviation, and plays an important role in transporting water, oil and natural gas.

[0003] Buried steel pipe is a commonly used pressure pipe in water resource allocation projects. During construction, trenches are first excavated, then pipes are laid, and soil and stone materials are backfilled and compacted. It has the advantages of simple structure, fast construction, convenient maintenance, and environmental friendliness. It is particularly suitable for pipeline projects with large diameters, high internal pressures, and complex external environments. The longer the pipeline is built, the more prominent the comprehensive benefits. With the increasing scale of water resource allocation projects, the HD value (the product of head and pipe diameter) of the pipeline will be very high, and it will rely more on large buried steel pipes (pipe diameter not less than 1.2m). Compared with the oil and gas, water supply and drainage, heating, gas and other industries, the water conservancy and hydropower industry often uses large buried steel pipes (maximum diameter can reach 4.0m), while the maximum diameter in the oil and gas industry is only 1.4m. When the diameter of the pipeline becomes larger, the complexity of production, construction and deformation control will increase exponentially. At present, the use of larger diameter pipelines is the common development direction of various industries. The construction process of large-diameter pipelines is very delicate, and supports are usually set inside the pipeline to prevent pipeline deformation during construction.

[0004] However, the current numerical simulation method for buried pipelines ignores the setting of supports inside the pipeline and the layered filling of backfill soil, which results in large errors compared with the actual situation. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent prediction method for the mechanical behavior of a buried pipeline during construction, which can accurately simulate the construction environment, optimize the construction plan, improve the construction quality, reduce the construction risk, and has significant technical advantages and application value.

[0006] To achieve the above object, the present invention provides an intelligent prediction method for mechanical behavior during the construction process of a buried pipeline, comprising the following steps: Step S1, defining geometric parameters, unit types and material parameters of a refined numerical simulation model of a buried pipeline construction process; Step S2, establishing a three-dimensional finite element model of the pipeline, cushion layer, backfill soil, original soil and internal support; Step S3, creating contact relationships between the steel pipe and the backfill soil, and between the backfill soil and the original soil, and setting contact parameters; Step S4, performing multi-stage load step simulation on the refined numerical simulation model of the buried pipeline construction process, including trench excavation, cushion layer installation, pipeline and internal support installation, backfilling of soil layer by layer, and removal of internal support; Step S5, designing an experimental scheme based on the orthogonal experimental method to obtain experimental data; Step S6: Relying on the Python platform, support vector regression and genetic algorithm are used to train and test the test data to build an intelligent prediction model for mechanical behavior; Step S7: using the intelligent prediction model for mechanical behavior to predict the mechanical behavior of the buried pipeline during construction.

[0007] Preferably, in step S1, the geometric parameters include pipe diameter, pipe burial depth, soil arc foundation center angle, cushion thickness, trench width, trench sidewall inclination, and length and width of the entire model.

[0008] Preferably, in step S1, the unit types include plane units, solid units, shell units and rod units.

[0009] Preferably, in step S1, the material parameters include: Elastic modulus, Poisson's ratio, density, linear expansion coefficient, and thickness of steel pipes; Elastic modulus, Poisson's ratio, density, cohesion, internal friction angle, expansion angle, and linear expansion coefficient of original soil, backfill soil, and cushion layer; Cross-sectional type, cross-sectional area, elastic modulus, Poisson's ratio, density, and linear expansion coefficient of the cross-shaped support.

[0010] Preferably, in step S2, establishing a three-dimensional finite element model includes: Create key points of the model according to the coordinates of each position, connect the points into lines, establish a linear contour, and then enclose the lines into a surface to create a two-dimensional plane model of the buried pipeline; Divide the plane horizontally and vertically to divide the two-dimensional plane grid of the buried pipeline, and drag the surface grid to form a three-dimensional finite element model of the buried pipeline; The key points of the M-shaped support are created along the circumference of the pipe, and are connected into lines in pairs to divide the M-shaped support grid and construct a grid model of the M-shaped support.

[0011] Preferably, in step S3, creating a contact relationship includes: Establish contact pairs between steel pipe and backfill soil, and between backfill soil and original soil, and set parameters such as contact type, friction coefficient, penalty stiffness, and initial gap; The ANSYS surface-to-surface contact method is used to simulate the surface-to-surface contact unit Target170-Contact174. Contact pairs are established on the unit surface, and the contact stress is calculated by penetrating the surrounding nodes.

[0012] Preferably, in step S4, the multi-stage load step simulation includes: Load step 1: Use the EKILL command to kill the elements of the soil, steel pipes, and cross-shaped supports in the trench, and apply full constraints to the nodes of the killed elements. Then apply gravity load and solve. After solving, release the dead element constraints. Load step 2: Use the EALIVE command to activate the cushion unit, apply full constraints to the killed unit points, reactivate the axial constraints of the cushion unit, solve, and release the dead unit constraints after solving; Load step 3: Use the EALIVE command to activate the pipe and the cross-shaped support, apply full constraints to the killed unit points, reactivate the axial constraints of the pipe unit, solve, and release the dead unit constraints after solving; Load steps 4 to 9: Use the EALIVE command to activate the backfill soil layer 1, apply full constraints to the killed unit points, reactivate the axial constraints of the backfill soil layer 1, and solve. After solving, release the dead unit constraints; according to the above method, use the loop command to activate the backfill soil layers 2, 3, 4, 5, and 6 in turn, and solve them layer by layer; Load step 10-15: According to the method of load step 4-9, use the loop command to activate the 7th, 8th, 9th, 10th, 11th and 12th layers of backfill soil in sequence and solve them layer by layer; Load step 16: Activate the 13th layer of backfill soil at the position of 0.3m above the pipe top and apply full constraints to the killed unit points, reactivate the axial constraints of the 1st layer of backfill soil, solve, and release the dead unit constraints after solving; Load step 17: Activate 14 layers of backfill soil at the position of 0.3m to 0.6m above the top of the pipe, apply full constraints to the killed unit points, reactivate the axial constraints of the soil layer, solve, and release the dead unit constraints after solving; Load step 18: Activate 15 layers of backfill soil from the top of the pipe to the ground at a position of 0.6 m. Apply full constraints to the killed unit points, reactivate the axial constraints of the soil layer, solve, and release the dead unit constraints after solving. Load step 19: Kill the elements of the cross brace.

[0013] Preferably, in step S6, constructing a mechanical behavior intelligent prediction model includes: Establish a GA-SVR model and use the GA algorithm to search for the penalty factor in the SVR model and width parameters , and then the optimal solution , Import the SVR model and build the GA-SVR model; The OED-GA-SVR coupling algorithm model was established, and the experimental schemes obtained by orthogonal experiments were used as the main control points of the prediction space. The distances between the main control points were linearly interpolated, and multiple groups of experimental schemes were supplemented. The supplemented experimental schemes were listed as auxiliary control points of the prediction space, and the independent variables and response quantities under each scheme were sorted out as the initial input data of the model. After normalization, multiple groups of sample data are used to train and test the proposed GA-SVR model.

[0014] Therefore, the present invention adopts the above-mentioned intelligent prediction method for mechanical behavior of buried pipeline construction process, and the beneficial technical effects are as follows: (1) Accurately simulate complex construction environments: By establishing a three-dimensional finite element model including pipelines, cushions, backfill soil, original soil and internal supports, the present invention can accurately simulate the complex environment and conditions during the construction of buried pipelines. This refined modeling method can capture key mechanical behaviors during the construction process, such as the interaction between the pipeline and the soil, the influence of internal supports, etc., thereby providing more accurate guidance for construction.

[0015] (2) Intelligent prediction of construction mechanical behavior: The present invention can accurately predict the mechanical behavior of buried pipelines during construction by using a numerical simulation scheme designed using the orthogonal test method and combining it with an intelligent prediction model constructed using support vector regression (SVR) and genetic algorithm (GA). This prediction capability helps to identify potential construction problems in advance, such as pipeline deformation and soil displacement, so that preventive measures can be taken to reduce construction risks.

[0016] (3) Optimize construction plan and improve construction quality: By evaluating the mechanical behavior under different construction schemes through intelligent prediction models, the present invention can help engineers select the optimal construction scheme, such as determining the appropriate internal support layout, backfill soil thickness, etc. This optimized construction scheme can improve construction quality, reduce uncertainty and potential problems during the construction process, and thus improve the reliability and durability of the entire project. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an intelligent prediction method for mechanical behavior during the construction process of a buried pipeline according to the present invention; Figure 2 It is a three-dimensional model of buried pipeline; Figure 2 (a) is the overall model; Figure 2 (b) is an enlarged view of the groove; Figure 3 It is a simulation process for the buried pipeline construction process; among them, Figure 3 (a) in the figure is step 1: trench excavation; Figure 3 (b) in the figure is step 2: installing the cushion layer; Figure 3 (c) in the figure is step 3: installing pipes and internal supports; Figure 3 (d) in the figure is step 4: trench laying and backfilling 1 layer of soil; Figure 3 (e) in the figure is step 5: laying 2 layers of backfill soil in the trench; Figure 3 (f) in the figure is step 6: laying 3 layers of backfill soil in the trench; Figure 3 (g) in the figure is step 7: laying 4 layers of backfill soil in the trench; Figure 3 (h) in the figure is step 8: laying 5 layers of backfill soil in the trench; Figure 3 (i) in the figure is step 9: laying 6 layers of backfill soil in the trench; Figure 3 (j) in the figure is step 10: trench laying and backfilling with 7 layers of soil; Figure 3 (k) in the figure is step 11: trench laying and backfilling with 8 layers of soil; Figure 3 (l) in the figure is step 12: trench laying and backfilling 9 layers of soil; Figure 3 The (m) in the figure is step 13: trench laying and backfilling 10 layers of soil; Figure 3 The (n) in the figure is step 14: trench laying and backfilling 11 layers of soil; Figure 3 (o) in the figure is step 15: trench laying and backfilling 12 layers of soil; Figure 3 (p) in the figure is step 16: trench laying and backfilling 13 layers of soil; Figure 3 (q) in the figure is step 17: trench laying and backfilling 14 layers of soil; Figure 3 (r) in the figure is step 18: trench laying and backfilling with 15 layers of soil; Figure 3 The (s) in the figure is step 19: removing the internal support; Figure 4 A flow chart for intelligent prediction of pipeline mechanical behavior during construction; Figure 5 Improve the calculation process of SVR model for GA algorithm. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0019] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0020] Embodiment 1 like Figure 1 FIG. 1 is a flow chart of an intelligent prediction method for mechanical behavior of a buried pipeline during construction according to the present invention, which specifically includes the following steps: Step 1: Define model geometry parameters, element types, and material parameters.

[0021] Define the geometric parameters of the refined numerical simulation model of the buried pipeline construction process: define the pipeline diameter, pipeline burial depth, soil arc foundation center angle, cushion thickness, trench width and trench side wall inclination, and define the length and width of the entire model.

[0022] Define the unit types: plane unit PLANE42 (used when creating a two-dimensional grid), solid unit SOLID185 (used for original soil, backfill soil and sand cushion), shell unit SHELL181 (used for steel pipes), and rod unit LINK180.

[0023] Define material parameters: set the material parameters of the steel pipe, including elastic modulus, Poisson's ratio, density, linear expansion coefficient, and thickness; set the material parameters of the original soil, backfill soil, and cushion layer, including elastic modulus, Poisson's ratio, density, cohesion, internal friction angle, expansion angle, and linear expansion coefficient; set the material parameters of the "M"-shaped support: section type, section area, elastic modulus, Poisson's ratio, density, and linear expansion coefficient.

[0024] Step 2: Establish a three-dimensional finite element model of the pipeline, cushion layer, backfill soil, original soil and "M"-shaped support ( Figure 2 ).

[0025] First, the key points of the model are created according to the coordinates of each position; the points are connected into lines to establish a linear contour; and then the lines are combined into a surface to create a two-dimensional plane model of the buried pipeline.

[0026] Next, the plane is divided horizontally and vertically to divide the two-dimensional plane grid of the buried pipeline, and the surface grid is dragged to form a three-dimensional finite element model of the buried pipeline.

[0027] Finally, eight key points of the "M"-shaped support were created along the circumference of the pipe and connected into lines in pairs to construct a separate "M"-shaped support. Then, through the complex offset command, a "M"-shaped support was set at intervals of 2 meters in the 3D finite element model of the buried pipeline and the grid was divided.

[0028] Step 3: Create the contact relationship between steel pipe-backfill soil and backfill soil-original soil.

[0029] The relationships between steel pipe and backfill soil and backfill soil and original soil are established respectively. Then, the contact pair between the two is established by using the ANSYS surface-surface contact method. The contact type, friction coefficient, penalty stiffness, initial gap and other parameters are set to generate the target surface and contact surface.

[0030] In the buried pipeline model, it is crucial to accurately simulate the pipe-soil interaction. In essence, this interaction involves the contact problem of the pipe-soil interface, accompanied by complex factors such as material, geometry and contact nonlinearity. Reasonable reproduction of pipe-soil contact behavior is the key to studying the force and deformation mechanism of buried pipelines. Therefore, surface-to-surface contact units (Target170-Contact174) are used for simulation during modeling. The surface-to-surface contact unit establishes contact pairs on the unit surface and calculates the contact stress by penetrating the surrounding nodes to reduce local stress concentration and uneven distribution of contact pressure. The interaction between the contact surfaces includes normal force and tangential force, among which the relative sliding state can be determined by the Coulomb friction model, that is: (1); In the formula, is the equivalent shear stress; is the maximum allowable shear stress; is the friction coefficient; is the normal pressure on the contact surface; For cohesion.

[0031] Step 4: Setup before solving.

[0032] Set parameters for model solution, turn on large deformation, use Newton-Laplace algorithm, turn on automatic time step, and impose normal displacement constraints on the top surface of the model, the bottom, left and right, and front and back positions.

[0033] Step 5: Perform multi-stage load step simulation on the refined numerical simulation model of the buried pipeline construction process, including trench excavation, cushion layer installation, pipeline and internal support installation, layer-by-layer backfilling, and removal of internal supports.

[0034] Load step 1: Trench excavation ( Figure 3 (a) in the figure.

[0035] The EKILL command is used to kill the soil, steel pipes, and "M"-shaped support units in the trench, and full constraints are applied to the nodes of the killed units. Next, gravity loads are applied and solved. After the solution is completed, the dead unit constraints are released.

[0036] Load step 2: Pad installation ( Figure 3 (b) in the figure.

[0037] Use the EALIVE command to activate the cushion unit, apply full constraints to the killed unit points, reactivate the axial constraints of the cushion unit, solve, and release the dead unit constraints after solving.

[0038] Load step 3: Installation of steel pipes and "M" shaped supports ( Figure 3 (c) in the figure.

[0039] Use the EALIVE command to activate the pipeline and the "M"-shaped support, apply full constraints to the killed unit points, reactivate the axial constraints of the pipeline unit, solve the problem, and release the dead unit constraints after the solution.

[0040] Load steps 4 to 9: Backfill the soil layer by layer between the cushion top and the pipe waist. Figure 3 (d) ~ Figure 3 (i) in the figure.

[0041] Use the EALIVE command to activate the backfill soil layer 1, apply full constraints to the killed unit points, reactivate the axial constraints of the backfill soil layer 1, perform the solution, and release the dead unit constraints after the solution.

[0042] Load step 10~15: Backfill soil layer by layer between pipe waist and pipe top ( Figure 3 (g) ~ Figure 3 (o) in the figure.

[0043] According to the method of load steps 4 to 9, use the loop command to activate the backfill layers 7, 8, 9, 10, 11, and 12 in sequence and solve them layer by layer.

[0044] Load step 16: Pipe top - 0.3m backfill soil laying on the top of the pipe ( Figure 3 (p) in the figure.

[0045] Activate the 13th layer of backfill soil at the position of 0.3m above the pipe top and apply full constraints to the killed unit points. Reactivate the axial constraints of the 1st layer of backfill soil and solve. After solving, release the dead unit constraints.

[0046] Load step 17: Backfill soil laying from 0.3m above the pipe top to 0.6m above the pipe top ( Figure 3 (q) in the figure.

[0047] Activate 14 layers of backfill soil at the position of 0.3m to 0.6m above the pipe top, apply full constraints to the killed unit points, reactivate the axial constraints of the soil layer, solve the problem, and release the dead unit constraints after the solution.

[0048] Load step 18: 0.6m above the pipe top - backfill soil laying on the ground ( Figure 3 (r) in the.

[0049] Activate 15 layers of backfill soil from the top of the pipe to the ground at a position of 0.6m. Apply full constraints to the killed unit points. Reactivate the axial constraints of the soil layer and solve. After solving, release the dead unit constraints.

[0050] Load step 19: Kill the elements of the cross brace ( Figure 3 in (s).

[0051] Step 6. To establish an intelligent prediction model for pipeline mechanical behavior during construction, based on the above-mentioned simulation of the buried pipeline construction process, the orthogonal test method (OED) was used to design the test plan. The orthogonal test plan that fully considers multiple factors such as pipeline, soil, number of backfill layers, trench shape, and burial depth was designed to obtain a large amount of test data. Based on the test data, the Python platform was used to train and test a large number of numerical simulation results, verify and correct the prediction model, and the analysis process is shown in the figure. Figure 4 .

[0052] Establish the GA-SVR model.

[0053] SVR is a general learning method based on the VC dimension theory and structural risk minimization theory in statistics. It has the characteristics of global optimization and small sample size, and has unique advantages in analyzing nonlinear mapping relationships. Group training samples, training set ,in is the input parameter, is the output parameter, is the parameter number, is a set of real numbers. Then in high-dimensional space Linear regression function on The expression is: (2); In the formula, To reflect the high-dimensional characteristics of the data set, is the weight vector, is the bias value.

[0054] The GA algorithm can realize implicit parallel computing and global search capabilities, and optimizes nonlinear complex problems by using the rule of "survival of the fittest" in biological theory. First, it forms genes by encoding chromosomes, and then uses gene expression methods such as selection, crossover, and mutation to achieve parameter optimization. and are two individuals in the population, respectively. and Encode them in binary format to get genes and , which can constitute genome G.

[0055] SVR model penalty factor and width parameters The sensitivity is high, but it is determined by experience or trial and error, which is highly unstable. The GA algorithm has strong global search capabilities and can adaptively search for the optimal solution. Therefore, the GA algorithm is used to search for the optimal SVR model. and , and then the optimal solution ( , ) Import the SVR model and build a GA-SVR model with higher accuracy, such as Figure 5 The detailed process is as follows: (a) Population initialization: using and Construct chromosomes and randomly select a chromosome for encoding to generate the initial population of chromosomes; (b) Fitness evaluation: Learn the training data set, determine the fitness value of the individual, and evaluate the fitness of the chromosome based on the size of the fitness value; (c) Genetic manipulation: Iterative replication of chromosomes using gene expression methods such as selection, crossover, and mutation; (d) Determine whether the termination condition is met: If and If there is no change or the maximum number of iterations is reached, the optimization is stopped and the optimal solution is output ( , ); (e) Parameter import: The optimal parameters ( , ) is imported into the SVR model for regression prediction.

[0056] Establish the OED-GA-SVR coupling algorithm model.

[0057] There are many factors involved in the construction of large-diameter buried steel pipes. How to reasonably design the analysis plan is a major problem. This project intends to establish an OED-GA-SVR coupling algorithm pipeline structure prediction model based on the orthogonal test (OED) scheme. During the analysis, the calculation scheme obtained by the orthogonal test is used as the main control point of the prediction space, and the distance between the main control points is linearly interpolated. Multiple groups of test schemes are supplemented, and the supplementary schemes are listed as auxiliary control points of the prediction space. The independent variables and response quantities under each scheme are sorted out as the initial input data of the model. In order to improve the stability of the regression model, multiple groups of sample data are normalized: (3); In the formula, Representation parameters Middle Sample values, is the parameter value normalized to [0, 1]. The normalized data samples are used to train and test the proposed GA-SVR model, with 80% of the training set samples and 20% of the test set samples.

[0058] In order to judge the regression effect of the model, the mean square error RMSE and the square sum correlation coefficient R are used. 2Evaluate the regression fitting effect of the model, the calculation formula is: (4); In the formula, and are the measured and predicted values ​​of the prediction indicators, is the number of samples, It is the measured average value of the indicator.

[0059] It is worth noting that the contents not elaborated in detail in the present invention are all prior art and are well known to those skilled in the art.

[0060] Therefore, the present invention adopts the above-mentioned intelligent prediction method of mechanical behavior in the construction process of buried pipelines, which can accurately simulate the construction environment, optimize the construction plan, improve the construction quality, reduce the construction risk, and has significant technical advantages and application value.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent prediction method for mechanical behavior of buried pipeline construction process, characterized in that: The following steps are involved: Step S1, defining geometric parameters, unit types and material parameters of a refined numerical simulation model of a buried pipeline construction process; Step S2, establishing a three-dimensional finite element model of the pipeline, cushion layer, backfill soil, original soil and internal support; Step S3, creating contact relationships between the steel pipe and the backfill soil, and between the backfill soil and the original soil, and setting contact parameters; Step S4, performing multi-stage load step simulation on the refined numerical simulation model of the buried pipeline construction process, including trench excavation, cushion layer installation, pipeline and internal support installation, backfilling of soil layer by layer, and removal of internal support; Step S5, designing an experimental scheme based on the orthogonal experimental method to obtain experimental data; Step S6: Relying on the Python platform, support vector regression and genetic algorithm are used to train and test the test data to build an intelligent prediction model for mechanical behavior; Step S7: using the intelligent prediction model for mechanical behavior to predict the mechanical behavior of the buried pipeline during construction.

2. According to claim 1, the intelligent prediction method for mechanical behavior of buried pipeline construction process is characterized in that: In step S1, the geometric parameters include the pipe diameter, the pipe burial depth, the soil arc foundation center angle, the cushion thickness, the trench width, the trench sidewall inclination angle, and the length and width of the entire model.

3. The intelligent prediction method for mechanical behavior of buried pipeline construction process according to claim 1 is characterized in that: In step S1, the unit types include plane unit, solid unit, shell unit and rod unit.

4. The intelligent prediction method for mechanical behavior of buried pipeline construction process according to claim 1 is characterized in that: In step S1, the material parameters include: Elastic modulus, Poisson's ratio, density, linear expansion coefficient, and thickness of steel pipes; Elastic modulus, Poisson's ratio, density, cohesion, internal friction angle, expansion angle, and linear expansion coefficient of original soil, backfill soil, and cushion layer; Cross-sectional type, cross-sectional area, elastic modulus, Poisson's ratio, density, and linear expansion coefficient of the cross-shaped support.

5. The intelligent prediction method for mechanical behavior of buried pipeline construction process according to claim 1 is characterized in that: In step S2, establishing a three-dimensional finite element model includes: Create key points of the model according to the coordinates of each position, connect the points into lines, establish a linear contour, and then enclose the lines into a surface to create a two-dimensional plane model of the buried pipeline; Divide the plane horizontally and vertically to divide the two-dimensional plane grid of the buried pipeline, and drag the surface grid to form a three-dimensional finite element model of the buried pipeline; The key points of the M-shaped support are created along the circumference of the pipe, and are connected into lines in pairs to divide the M-shaped support grid and construct a grid model of the M-shaped support.

6. The intelligent prediction method for mechanical behavior of buried pipeline construction process according to claim 1 is characterized in that: In step S3, creating a contact relationship includes: Establish contact pairs between steel pipe and backfill soil, and between backfill soil and original soil, and set contact type, friction coefficient, penalty stiffness, and initial gap; The ANSYS surface-to-surface contact method is used to simulate the surface-to-surface contact unit Target170-Contact174. Contact pairs are established on the unit surface, and the contact stress is calculated by penetrating the surrounding nodes.

7. The intelligent prediction method for mechanical behavior of buried pipeline construction process according to claim 1 is characterized in that: In step S4, the multi-stage load step simulation includes: Load step 1: Use the EKILL command to kill the elements of the soil, steel pipes, and cross-shaped supports in the trench, and apply full constraints to the nodes of the killed elements. Then apply gravity load and solve. After solving, release the dead element constraints. Load step 2: Use the EALIVE command to activate the cushion unit, apply full constraints to the killed unit points, reactivate the axial constraints of the cushion unit, solve, and release the dead unit constraints after solving; Load step 3: Use the EALIVE command to activate the pipe and the cross-shaped support, apply full constraints to the killed unit points, reactivate the axial constraints of the pipe unit, solve, and release the dead unit constraints after solving; Load steps 4 to 9: Use the EALIVE command to activate the backfill soil layer 1, apply full constraints to the killed unit points, reactivate the axial constraints of the backfill soil layer 1, and solve. After solving, release the dead unit constraints; according to the above method, use the loop command to activate the backfill soil layers 2, 3, 4, 5, and 6 in turn, and solve them layer by layer; Load step 10-15: According to the method of load step 4-9, use the loop command to activate the 7th, 8th, 9th, 10th, 11th and 12th layers of backfill soil in sequence and solve them layer by layer; Load step 16: Activate the 13th layer of backfill soil at the position of 0.3m above the pipe top and apply full constraints to the killed unit points, reactivate the axial constraints of the 1st layer of backfill soil, solve, and release the dead unit constraints after solving; Load step 17: Activate 14 layers of backfill soil at the position of 0.3m to 0.6m above the top of the pipe, apply full constraints to the killed unit points, reactivate the axial constraints of the soil layer, solve, and release the dead unit constraints after solving; Load step 18: Activate 15 layers of backfill soil from the top of the pipe to the ground at a position of 0.6 m. Apply full constraints to the killed unit points, reactivate the axial constraints of the soil layer, solve, and release the dead unit constraints after solving. Load step 19: Kill the elements of the cross brace.

8. The intelligent prediction method for mechanical behavior of buried pipeline construction process according to claim 7 is characterized in that: In step S6, constructing a mechanical behavior intelligent prediction model includes: Establish a GA-SVR model and use the GA algorithm to search for the penalty factor in the SVR model and width parameters , and then the optimal solution , Import the SVR model and build the GA-SVR model; The OED-GA-SVR coupling algorithm model was established, and the experimental schemes obtained by orthogonal experiments were used as the main control points of the prediction space. The distances between the main control points were linearly interpolated, and multiple groups of experimental schemes were supplemented. The supplemented experimental schemes were listed as auxiliary control points of the prediction space, and the independent variables and response quantities under each scheme were sorted out as the initial input data of the model. After normalization, multiple groups of sample data are used to train and test the proposed GA-SVR model.

Images