Method for dynamically and intelligently determining supporting parameters of super-long large pipe shed of shallow-buried high-speed rail tunnel

Abstract

The invention discloses a method for dynamically and intelligently determining support parameters of an ultra-long large pipe shed of a shallow-buried high-speed rail tunnel. The method comprises the following steps: S1, selecting key parameters of the ultra-long large pipe shed which have obvious influence on the support effect of the shallow-buried tunnel; s2, constructing a database of maximum stratum deformation and maximum stratum stress under different stratum conditions and support conditions; s3, establishing an intelligent determination model for the key parameters of the ultra-long large pipe shed; s4, optimizing hyper-parameters of the intelligent model, collecting stratum condition parameters in real time, and substituting the stratum condition parameters into the intelligent model to obtain super-long large pipe shed support key parameters suitable for the current stratum condition; according to the dynamic intelligent determination method for the support parameters of the super-long large pipe shed of the shallow-buried high-speed rail tunnel, the problem that the pipe shed parameters determined by a theoretical formula are not accurate is solved; a theoretical formula is difficult to master and use by field technicians; and the theoretical formula cannot be suitable for variable geological conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel engineering, and in particular to a method for dynamically intelligently determining support parameters of an extra-long pipe shed in a shallow-buried high-speed railway tunnel. Background Art

[0002] With the rapid development of high-speed railways, the demand for tunnel construction under complex geological conditions is increasing. Especially under shallow buried conditions, the construction risk of tunnels is high, and effective support technology is needed to ensure construction safety. Pipe-roof support, as an effective advance support technology, is widely used in underground structure engineering. It plays a temporary advance support role by pre-setting steel pipes with large moment of inertia on the lining arch ring of underground tunnels or structures to prevent soil collapse and surface subsidence.

[0003] Generally speaking, the design parameters of pipe-roof support will be different for different geological conditions and different tunnel working conditions. Therefore, it becomes very complicated to determine the optimal parameter combination of pipe-roof support. Especially for complex and changeable geological conditions, when ultra-long pipe-roof technology is required, it becomes particularly difficult to determine reasonable pipe-roof support parameters. Therefore, in order to improve the efficiency and accuracy of determining pipe-roof support parameters, intelligent algorithms are explored to achieve dynamic optimization and intelligent recommendation of pipe-roof support parameters.

[0004] The existing parameters of super-long pipe roofs for shallow buried tunnels are often determined by theoretical formulas, which have the following disadvantages: the theoretical formulas have many assumptions, resulting in inaccurate pipe roof parameters; the theoretical formulas are complex to determine the pipe roof parameters and are difficult for on-site technicians to master and use; the theoretical formulas are often fixed and cannot be applied to changing geological conditions. Summary of the invention

[0005] The purpose of the present invention is to provide a method for dynamically and intelligently determining the support parameters of super-long pipe roofs in shallow high-speed railway tunnels, so as to solve the problems that the parameters of super-long pipe roofs in existing shallow tunnels are often determined by theoretical formulas, and the theoretical formulas have many assumptions, resulting in inaccurate determined pipe roof parameters; the pipe roof parameters determined by the theoretical formulas are complex and difficult for on-site technicians to master and use; and the pipe roof parameters determined by the theoretical formulas are often fixed and cannot be applied to changeable geological conditions.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for dynamically and intelligently determining support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel, the method comprising the following steps:

[0007] S1: Select the key parameters of the super-long pipe shed that have a significant impact on the support effect of shallow buried tunnels;

[0008] S2: Construct a database of maximum formation deformation and maximum formation stress under different formation conditions and support conditions;

[0009] S3: Establish an intelligent model for determining key parameters of super-long pipe sheds;

[0010] S4: Optimize the hyperparameters of the intelligent model, collect the formation condition parameters in real time, substitute them into the intelligent model, and obtain the key parameters of the super-long pipe rack support suitable for the current formation conditions.

[0011] Preferably, the key parameters of the extra-long pipe shed that significantly affect the support effect of the shallow tunnel in step S1 include the pipe shed diameter, the pipe shed spacing, the pipe shed external insertion angle, the arrangement of steel bars inside the pipe shed, the pipe shed grouting pressure, etc.

[0012] Preferably, the specific steps of S2 include:

[0013] Based on actual geological survey data and geological conditions, a stratum model is established, different pipe-roof support parameters are set, and a support structure model is established;

[0014] Use numerical methods to calculate formation deformation and formation stress;

[0015] By analyzing the degree of stratum deformation, the distribution of stratum stress, the stability of the support structure, etc., the degree of stratum deformation and the distribution of stratum stress under different stratum conditions and support conditions are obtained, and a database of maximum stratum deformation and maximum stratum stress under different stratum conditions and support conditions is constructed.

[0016] Preferably, the specific step S3 includes using the data in the established database, taking the formation conditions, maximum formation deformation and maximum formation stress as input variables, and taking the key parameters of the super-long pipe rack support as output variables, to construct an intelligent determination model for the key parameters of the super-long pipe rack support.

[0017] Preferably, in step S4, the intelligent model parameters are optimized by installing sensors in the tunnel construction area to monitor the stratum deformation during the super-long pipe rack support construction in real time, and providing feedback to the model to optimize the intelligent model hyperparameters.

[0018] It can be seen from the above technical solution that the present invention has the following beneficial effects:

[0019] The method for dynamically and intelligently determining the parameters of super-long pipe-roof support for shallow-buried high-speed railway tunnels can more effectively control the stratum deformation during tunnel construction, reduce construction risks, and improve construction safety by intelligently determining the parameters of pipe-roof support. The method can adjust the pipe-roof support parameters according to real-time monitoring data, reduce construction delays caused by inappropriate parameters, and improve construction efficiency. Reasonable pipe-roof support parameters can reduce material waste, reduce construction costs, and reduce economic losses caused by construction accidents. High-speed railway tunnels often pass through a variety of complex geological conditions. The dynamic intelligent determination method can adjust the support parameters according to real-time geological changes and adapt to different geological environments. It solves the problem that the parameters of super-long pipe-roof for existing shallow-buried tunnels are often determined by theoretical formulas, and the theoretical formulas have many assumptions, resulting in inaccurate determined pipe-roof parameters; the theoretical formulas are complex to determine the pipe-roof parameters, which are difficult for on-site technicians to master and use; and the theoretical formulas are often fixed and cannot be applied to variable geological conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the method of the present invention; DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, a method for dynamically and intelligently determining support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel comprises the following steps:

[0023] S1: Select the key parameters of the super-long pipe shed that have a significant impact on the support effect of shallow buried tunnels;

[0024] S2: Construct a database of maximum formation deformation and maximum formation stress under different formation conditions and support conditions;

[0025] S3: Establish an intelligent model for determining key parameters of super-long pipe sheds;

[0026] S4: Optimize the hyperparameters of the intelligent model, collect the formation condition parameters in real time, substitute them into the intelligent model, and obtain the key parameters of the super-long pipe rack support suitable for the current formation conditions.

[0027] By intelligently determining the pipe-roof support parameters, the ground deformation during tunnel construction can be more effectively controlled, construction risks can be reduced, and construction safety can be improved. The dynamic intelligent determination method can adjust the pipe-roof support parameters according to real-time monitoring data, reduce construction delays caused by inappropriate parameters, and improve construction efficiency. Reasonable pipe-roof support parameters can reduce material waste, reduce construction costs, and reduce economic losses caused by construction accidents. High-speed rail tunnels often pass through a variety of complex geological conditions. The dynamic intelligent determination method can adjust the support parameters according to real-time geological changes to adapt to different geological environments.

[0028] The above method specifically comprises the following steps:

[0029] First, select the key parameters of the super-long pipe shed support. Refer to the relevant specifications of the pipe shed support for shallow buried tunnels, and combine the construction technology of the pipe shed support for shallow buried tunnels to select the key parameters of the super-long pipe shed that have a significant impact on the support effect of shallow buried tunnels, such as the pipe shed diameter, pipe shed spacing, pipe shed external insertion angle, pipe shed internal steel bar arrangement, pipe shed grouting pressure, etc.

[0030] Based on the actual geological survey data and geological conditions, a stratum model is established, different pipe-roof support parameters are set, and a support structure model is established. Numerical methods such as the finite element method and the boundary element method are used. The finite element method is a numerical technique for solving approximate solutions to boundary value problems of partial differential equations. When solving, the entire problem area is decomposed, and each sub-area becomes a simple part, which is called a finite element. It uses the variational method to minimize the error function and produce a stable solution. Analogous to the idea of ​​connecting multiple small straight lines to approximate a circle, the finite element method includes all possible methods, which connect many simple equations on small areas called finite elements and use them to estimate complex equations on larger areas. It regards the solution domain as consisting of many small interconnected sub-domains called finite elements, assumes a suitable (simpler) approximate solution for each unit, and then derives the conditions that satisfy the domain (such as the equilibrium conditions of the structure) to obtain the solution to the problem. This solution is not an exact solution, but an approximate solution, because the actual problem is replaced by a simpler problem. Since most practical problems are difficult to get accurate solutions, and the finite element method not only has high calculation accuracy, but also can adapt to various complex shapes, it has become an effective engineering analysis method. The boundary element method is a new numerical method developed after the finite element method. Different from the basic idea of ​​dividing units in the continuous domain of the finite element method, the boundary element method only divides units on the boundary of the definition domain and uses functions that satisfy the control equation to approximate the boundary conditions. Therefore, compared with the finite element method, the boundary element method has the advantages of fewer units and simpler data preparation. However, when using the boundary element method to solve nonlinear problems, the regional integral corresponding to the nonlinear term is encountered. This integral has strong singularity near the singular point, making it difficult to solve. The formation deformation and formation stress are calculated, and the degree of formation deformation, the distribution of formation stress, the stability of the support structure, etc. are analyzed. Finally, the degree of formation deformation under different formation conditions and support conditions, the distribution of formation stress, and the database of maximum formation deformation and maximum formation stress under different formation conditions and support conditions are constructed;

[0031] Establish an intelligent determination model for the key parameters of super-long pipe sheds, with the help of machine learning methods such as random forest algorithm. Random forest is an integrated learning algorithm based on decision trees. It predicts by constructing multiple decision trees (i.e., "forests"). In the construction process of each decision tree, random sampling is adopted to extract samples from the data set for training, and features are randomly selected for node splitting. This randomness helps to reduce the overfitting of the model to the training data and improve the overall prediction performance. Random forest can be used for classification and regression problems. For example, it is widely used in medical diagnosis, financial fraud detection, text classification and other fields. Its advantages lie in processing high-dimensional data, evaluating feature importance, anomaly detection and missing value processing. The prediction result of random forest is obtained by integrating the prediction results of all decision trees, which can be voting (for classification problems) or taking the average value (for regression problems). Using the data in the established database, with formation conditions, maximum formation deformation and maximum formation stress as input variables, and super-long pipe shed support key parameters as output variables, an intelligent determination model for super-long pipe shed support key parameters is constructed. The model can predict the optimal combination of key support parameters based on real-time collected data and existing knowledge to ensure construction safety and efficiency;

[0032] Sensors installed in the tunnel construction area monitor the ground deformation during the construction of the super-long pipe shed in real time, provide feedback to the model, and optimize the hyperparameters of the intelligent model;

[0033] During the excavation of shallow tunnels, the formation condition parameters are collected in real time and substituted into the intelligent model to obtain the key parameters of the super-long pipe-roof support suitable for the current formation conditions, thereby realizing dynamic intelligent adjustment of the key parameters of the super-long pipe-roof support.

[0034] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for dynamically and intelligently determining the support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel, characterized in that: The method comprises the following steps: S1: Select the key parameters of the super-long pipe shed that have a significant impact on the support effect of shallow buried tunnels; S2: Construct a database of maximum deformation and maximum formation stress under different formation conditions and support conditions; S3: Establish an intelligent model for determining key parameters of super-long pipe sheds; S4: Optimize the hyperparameters of the intelligent model, collect the formation condition parameters in real time, substitute them into the intelligent model, and obtain the key parameters of the super-long pipe rack support suitable for the current formation conditions.

2. According to claim 1, a method for dynamically and intelligently determining support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel is characterized in that: In step S1, the key parameters of the super-long pipe shed that have a significant impact on the support effect of the shallow tunnel include the pipe shed diameter, the pipe shed spacing, the pipe shed external insertion angle, the arrangement of steel bars inside the pipe shed, the pipe shed grouting pressure, etc.

3. According to claim 1, a method for dynamically and intelligently determining support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel is characterized in that: The specific steps of S2 include: Based on actual geological survey data and geological conditions, a stratum model is established, different pipe-roof support parameters are set, and a support structure model is established; Use numerical methods to calculate formation deformation and formation stress; By analyzing the degree of stratum deformation, the distribution of stratum stress, the stability of the support structure, etc., the degree of stratum deformation and the distribution of stratum stress under different stratum conditions and support conditions are obtained, and a database of maximum stratum deformation and maximum stratum stress under different stratum conditions and support conditions is constructed.

4. According to claim 1, a method for dynamically and intelligently determining support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel is characterized in that: The specific step S3 includes using the data in the established database, taking the formation conditions, maximum formation deformation and maximum formation stress as input variables, and taking the key parameters of the super-long pipe rack support as output variables, to construct an intelligent determination model for the key parameters of the super-long pipe rack support.

5. According to claim 1, a method for dynamically and intelligently determining support parameters of an extra-long pipe shed for a shallow high-speed railway tunnel is characterized in that: In step S4, the intelligent model parameters are optimized by installing sensors in the tunnel construction area to monitor the stratum deformation during the super-long pipe rack support construction in real time, and providing feedback to the model to optimize the intelligent model hyperparameters.

Images