Method and system for determining influence factors of high-ground-temperature tunnel

Abstract

The invention provides a high-ground-temperature tunnel influence factor determination method and system, and belongs to the technical field of tunnel construction management, and the method comprises the steps: S1, obtaining a maximum lining temperature value and a plurality of influence parameters; s2, establishing a multiple linear regression analysis model based on the maximum value of the lining temperature and a plurality of influence parameters; s3, calculating a standardization coefficient Beta value of the multiple linear regression analysis model by utilizing statistical analysis software; and S4, determining influence factors of the high-ground-temperature tunnel according to the standardization coefficient Beta value. According to the method, the multiple linear regression model is applied to temperature field prediction of the tunnel lining structure, influence factors with remarkable influences can be identified, on one hand, the prediction accuracy of the high-ground-temperature tunnel is improved, on the other hand, valuable reference can be provided for manual intervention cooling, and the method is suitable for popularization and application. And construction of the high-ground-temperature tunnel and selection of cooling measures are facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of tunnel construction management, and specifically relates to a method and system for determining influencing factors of a high ground temperature tunnel. Background Art

[0002] During the tunnel construction process, the problem of high geothermal tunnels caused by geothermal heat cannot be ignored. In a high geothermal environment, the outer surface of the lining is subjected to the high temperature of the surrounding rock, and the inner surface temperature is consistent with the construction environment. The temperature difference between the inside and outside causes the tunnel to form a surrounding rock-lining-airflow heat transfer system. Heat conduction, heat convection and heat radiation are constantly carried out between the three, and the tunnel surrounding rock temperature field is constantly changing. Affected by the tunnel surrounding rock temperature field, the inner and outer surfaces of the lining produce different degrees of thermal expansion, causing the lining to produce temperature additional stress and cracking. In addition, when spraying concrete, the temperature difference causes poor concrete bonding performance, which is not conducive to the construction of high geothermal tunnels.

[0003] See the patent document with application number CN202410235444.7, which discloses an infrared scanning robot and a method for predicting the temperature of the surrounding rock of the main tunnel based on the advanced flat guide. By using the temperature of the side wall of the advanced flat guide tunnel combined with the borehole temperature data, based on the distribution law of rock heat conduction and temperature gradient, the location and range of the high-temperature thermal anomaly area are preliminarily delineated, and it is applied as a reference model to the heat source inversion to obtain the three-dimensional spatial distribution of the heat source intensity of the surrounding rock in front of the main tunnel, thereby realizing the positioning and identification of the high-temperature heat source. Although the patent document proposes that the location and range of the high-temperature thermal anomaly area can be delineated and inverted to realize the positioning and identification of the high-temperature heat source, it is impossible to determine the corresponding influence degree of the influencing factors of the high temperature (high ground temperature) of the tunnel, so it is impossible to make a reference value for human intervention, which affects the bonding performance of concrete. Summary of the invention

[0004] As described in the above background technology, the prior art is unable to determine the corresponding degree of influence of the influencing factors of high tunnel temperature (high ground temperature), resulting in a technical problem that there is no reference value for manual intervention. To address this technical problem, the present invention proposes a method and system for determining the influencing factors of high ground temperature tunnels.

[0005] The present invention applies the multivariate linear regression model to the temperature field prediction of the tunnel lining structure, and establishes a multivariate linear regression analysis model of influencing parameters and the maximum lining temperature, which can identify influencing factors with significant influence. On the one hand, it improves the prediction accuracy of high geothermal tunnels, and on the other hand, it can provide valuable reference for artificial intervention cooling, which is helpful for the construction of high geothermal tunnels and the selection of cooling measures.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] The present invention provides a method for determining influencing factors of a high ground temperature tunnel, comprising the following steps:

[0008] S1: Obtain the maximum lining temperature and multiple influencing parameters;

[0009] S2: Establish a multivariate linear regression analysis model based on the maximum lining temperature and multiple influencing parameters;

[0010] S3: Calculate the standardized coefficient Beta value of the multivariate linear regression analysis model using statistical analysis software;

[0011] S4: Determine the influencing factors of high ground temperature tunnels based on the standardized coefficient Beta value;

[0012] Among them, Beta ≥ 0.5 is a first-level influencing factor;

[0013] 0.1≤Beta<0.5, which is a secondary influencing factor;

[0014] Beta<0.1, which is a third-level influencing factor.

[0015] It is further defined that step S3 specifically includes:

[0016] S3.1: Use statistical analysis software to calculate the standardized coefficient Beta value and VIF value of the multivariate linear regression analysis model;

[0017] If VIF≤10, there is no multicollinearity between the influencing parameters, and the process continues to step S4, where the VIF value refers to the collinearity index;

[0018] If VIF>10, there is multicollinearity among the influencing parameters, and then continue with step S3.2;

[0019] S3.2: Use the ridge regression analysis method to perform nonlinear optimization on each influencing parameter until VIF≤10, and then continue to step S4.

[0020] It is further defined that the calculation model corresponding to the ridge regression analysis method in step S2.2 is:

[0021]

[0022] Where X is the matrix formed by the influencing parameters; T is the transposed sign; k is the ridge parameter; I is the unit matrix; Y is the matrix formed by the maximum lining temperature; is the ridge regression estimator.

[0023] It is further defined that in step S2, the multivariate linear regression analysis model is:

[0024] Y=β0+β1X1+β2X2+…+β m Xm +ε

[0025] Where Y is the matrix formed by the maximum lining temperature; β0, β1, …, β m are regression coefficients; X0, X1, …, X m are the influencing parameters; ε is the random error.

[0026] It is further defined that the method for determining the influencing factors of the high geothermal tunnel also includes:

[0027] S5: Eliminate the third-level influencing factors, take the first-level influencing factors as the main influencing factors, and take the second-level influencing factors as the secondary influencing factors.

[0028] It is further defined that the influencing parameters include tunnel face distance, porosity, thermal conductivity of surrounding rock, initial temperature of surrounding rock, wind flow temperature and / or convection heat transfer coefficient.

[0029] It is further defined that in step S3, the statistical analysis software is SPSS statistical analysis software.

[0030] The present invention provides a high geothermal tunnel influencing factor determination system, which is applied to the above-mentioned high geothermal tunnel influencing factor determination method, comprising:

[0031] Parameter acquisition module: used to obtain the maximum lining temperature and multiple influencing parameters;

[0032] Model building module: used to establish a multivariate linear regression analysis model based on the maximum lining temperature and multiple influencing parameters;

[0033] Statistical analysis module: used to calculate the standardized coefficient Beta value of the multivariate linear regression analysis model using statistical analysis software;

[0034] and an influencing factor determination module: used to determine the influencing factors of high ground temperature tunnels according to the standardized coefficient Beta value;

[0035] Among them, Beta ≥ 0.5 is a first-level influencing factor;

[0036] 0.1≤Beta<0.5, which is a secondary influencing factor;

[0037] Beta<0.1, which is a third-level influencing factor.

[0038] The present invention provides a storage medium storing a program file, wherein the program file is executed to implement the above-mentioned method for determining influencing factors of a high geothermal tunnel.

[0039] The present invention provides an electronic device, comprising a processor and a memory coupled to each other, wherein:

[0040] The memory is used to store the method for determining the influencing factors of the high ground temperature tunnel described above;

[0041] The processor is used to execute program instructions stored in the memory.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention provides a method for determining influencing factors of high geothermal tunnels. A multivariate linear regression analysis model is established for the maximum lining temperature and multiple influencing parameters. The multivariate linear regression model is applied to the temperature field prediction of the tunnel lining structure. The influencing factors with significant influence (primary influencing factors and secondary influencing factors) can be identified. On the one hand, the prediction accuracy of high geothermal tunnels is improved. On the other hand, it can provide valuable reference for artificial intervention cooling, which is helpful for the construction of high geothermal tunnels and the selection of cooling measures. For example, cooling measures are preferentially collected for the structure corresponding to the primary influencing factors.

[0044] 2. A method for determining influencing factors of high geothermal tunnels of the present invention, when VIF>10, the VIF value is processed according to the ridge regression analysis method so that there is no multicollinearity between the influencing parameters. As the k value increases, the VIF value becomes smaller and smaller, and the collinearity between the influencing parameters is eliminated. When the k value increases to 0.1 to 0.3, the ridge regression estimator of each regression coefficient is basically stable.

[0045] 3. The present invention provides a method for determining influencing factors of a high geothermal tunnel, which also includes eliminating the third-level influencing factors, taking the first-level influencing factors as the main influencing factors, and taking the second-level influencing factors as the secondary influencing factors, so as to more specifically take different cooling measures for the structures corresponding to the first-level influencing factors and the structures corresponding to the second-level influencing factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of a method for determining influencing factors of a high ground temperature tunnel according to the present invention;

[0047] Figure 2 It is a schematic diagram of the system for determining the influencing factors of high geothermal tunnels according to the present invention. DETAILED DESCRIPTION

[0048] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings and embodiments, but the present invention is not limited to the implementation modes described below.

[0049] Example 1

[0050] The temperature data of the lining under the influence of various influencing parameters during the construction period of the high geothermal tunnel are calculated, where the temperature data is the maximum lining temperature, and the influencing parameters include the distance from the tunnel face, porosity, thermal conductivity of the surrounding rock, initial temperature of the surrounding rock, wind flow temperature and / or convection heat transfer coefficient.

[0051] See also Figure 1 The present embodiment provides a method for determining influencing factors of a high ground temperature tunnel, which comprises the following steps:

[0052] S1: Obtain the maximum lining temperature and multiple influencing parameters.

[0053] S2: A multiple linear regression analysis model is established based on the maximum lining temperature and multiple influencing parameters; the multiple linear regression analysis model is:

[0054] Y=β0+β1X1+β2X2+…+β m X m +ε

[0055] Where Y is the matrix formed by the maximum lining temperature; β0, β1, …, β m are regression coefficients, where β0, β1, …, β m The values ​​of X0, X1, ..., X m are the influencing parameters; ε is the random error.

[0056] S3: Calculate the standardized coefficient Beta value of the multivariate linear regression analysis model using statistical analysis software; the calculation model corresponding to the ridge regression analysis method is:

[0057]

[0058] Wherein, X is the matrix formed by the influencing parameters; T is the transposition symbol; k is the ridge parameter, and the selection of k has a great influence on the performance of the calculation model corresponding to the ridge regression analysis method. Generally, the optimal value is found through the ridge trace diagram. In the present invention, k is preferably any value between 0.1 and 0.3, and specifically can be 0.1, 0.15, 0.2, 0.25 or 0.3; I is the unit matrix; Y is the matrix formed by the maximum value of the lining temperature; is the ridge regression estimator.

[0059] S4: Determine the influencing factors of high ground temperature tunnels based on the standardized coefficient Beta value;

[0060] Among them, Beta ≥ 0.5 is a first-level influencing factor;

[0061] 0.1≤Beta<0.5, which is a secondary influencing factor;

[0062] Beta<0.1, which is a third-level influencing factor.

[0063] This embodiment applies the multivariate linear regression model to the temperature field prediction of the tunnel lining structure, and identifies the influencing factors with significant influence (primary and secondary factors). On the one hand, it improves the prediction accuracy of high geothermal tunnels, and on the other hand, it can provide valuable reference for artificial intervention cooling, which is helpful for the construction of high geothermal tunnels and the selection of cooling measures.

[0064] In this embodiment, step S3 specifically includes:

[0065] S3.1: Use statistical analysis software to calculate the standardized coefficient Beta value and VIF value of the multivariate linear regression analysis model;

[0066] If the VIF value is ≤10, there is no multicollinearity between the influencing parameters, and the process continues to step S4, where the VIF value refers to the collinearity index;

[0067] If the VIF value is > 10, there is multicollinearity between the influencing parameters, and then continue with step S3.2;

[0068] S3.2: Use the ridge regression analysis method to perform nonlinear optimization on each influencing parameter until the VIF value is ≤10, and then continue to step S4.

[0069] This embodiment uses the ridge regression analysis method to process the VIF value so that there is no multicollinearity between the influencing parameters.

[0070] This embodiment provides a method for determining influencing factors of a high ground temperature tunnel, which further includes:

[0071] S5: Eliminate the third-level influencing factors, take the first-level influencing factors as the main influencing factors, and take the second-level influencing factors as the secondary influencing factors, so as to take different cooling measures for the structures corresponding to the first-level influencing factors and the structures corresponding to the second-level influencing factors in a more targeted manner.

[0072] In this embodiment, in step S3, the statistical analysis software is SPSS statistical analysis software. It should be noted that it is not limited to SPSS statistical analysis software, SAS software, R software, etc., as long as it can realize the statistical analysis software of the multivariate linear regression model.

[0073] Applying the method for determining influencing factors of high geothermal tunnels of the present invention to a decision support system for tunnel construction helps the decision support system to take different cooling measures for influencing factors of different levels.

[0074] It is necessary that before establishing the multivariate linear regression analysis, the influencing parameters and the maximum lining temperature should be dimensionally processed to eliminate the influence of different dimensions and dimensional units on data analysis and the establishment of the multivariate linear regression model, so as to improve the accuracy of the multivariate linear regression model.

[0075] In this embodiment, the standardized coefficient Beta is the regression coefficient value when the constant is 0, and its absolute value represents the influence degree of each influencing factor on the maximum value of the lining temperature. If it is positive, it is a positive correlation, and if it is negative, it is a negative correlation.

[0076] Taking the data in the multivariate regression analysis parameter table in Table 1 as an example, this embodiment is specifically described:

[0077] Table 1: Multiple regression analysis parameters

[0078]

[0079]

[0080] A multiple linear regression analysis model is established based on the maximum lining temperature and multiple influencing parameters. The multiple linear regression analysis model is:

[0081] Y=β0+β1X1+β2X2+…+β m X m +ε

[0082] Where, the matrix formed by the maximum lining temperature; β0, β1, …, β m are regression coefficients; X0, X1, …, X m are the influencing parameters; ε is the random error.

[0083] SPSS statistical analysis software was used to analyze and calculate the multivariate linear regression analysis model, and the standardized coefficient Beta value was obtained. The independent variables (influencing parameters) that have a significant impact on the lining temperature were identified, and the independent variables (influencing parameters) with insignificant coefficients were eliminated. The VIF value was used to determine whether there was a collinearity problem between the influencing parameters.

[0084] Table 2: Results of regression analysis of surrounding rock lining temperature

[0085]

[0086] B is the unstandardized regression coefficient, and the unstandardized regression coefficient is used in the multivariate linear regression analysis model; the standard error is the intermediate calculated value, indicating the fluctuation of the B value; the standardized coefficient Beta is the regression coefficient value when the constant is 0, which can be used to compare the influence of the independent variable (various influencing parameters) on the dependent variable (maximum lining temperature). The larger the value, the greater the influence; VIF is the collinearity index, and the value is less than or equal to 10, which means that the model has no multicollinearity problem. 2 It is the correlation coefficient of the multiple linear regression analysis model, which indicates the explanatory power of the independent variables (various influencing parameters) on the dependent variable (maximum lining temperature). It is between 0 and 1, and the closer it is to 1, the better the fit.

[0087]

[0088] In the formula, VIF is the collinearity index; R 2 is the correlation coefficient of the multiple linear regression analysis model.

[0089] As can be seen from Table 2, the VIF values ​​of each influencing factor are less than 10, so there is no multicollinearity problem. The lining temperature is negatively correlated with the distance from the tunnel face (-0.438) and the convective heat transfer coefficient (-0.258); it is positively correlated with the porosity (0.069), thermal conductivity (0.283), initial temperature of the surrounding rock (0.678) and wind flow temperature (0.364). The degree of influence is from large to small: initial temperature of the surrounding rock, distance from the tunnel face, wind flow temperature, thermal conductivity of the surrounding rock, convective heat transfer coefficient, porosity. Correspondingly, the initial temperature of the surrounding rock Beta is above 0.5, the first-level influencing factor, and the influence is extremely significant; the distance from the tunnel face, wind flow temperature, and convective heat transfer coefficient Beta are between 0.1-0.5, the second-level influencing factors, and the influence is significant; the Beta value of porosity is below 0.1, the third-level influencing factor, and the influence is not significant.

[0090] Example 2

[0091] See also Figure 2 , this embodiment is a high geothermal tunnel influencing factor determination system, which is applied to the high geothermal tunnel influencing factor determination method of embodiment 1, and includes a parameter acquisition module, a model building module, a statistical analysis module and an influencing factor determination module;

[0092] Parameter acquisition module: used to obtain the maximum lining temperature and multiple influencing parameters;

[0093] Model building module: used to establish a multivariate linear regression analysis model based on the maximum lining temperature and multiple influencing parameters;

[0094] Statistical analysis module: used to calculate the standardized coefficient Beta value of the multivariate linear regression analysis model using statistical analysis software;

[0095] Influencing factor determination module: used to determine the influencing factors of high ground temperature tunnels according to the standardized coefficient Beta value;

[0096] Among them, Beta ≥ 0.5 is a first-level influencing factor;

[0097] 0.1≤Beta<0.5, which is a secondary influencing factor;

[0098] Beta<0.1, which is a third-level influencing factor.

[0099] The high geothermal tunnel influencing factor determination system in this embodiment corresponds to the high geothermal tunnel influencing factor determination method in Example 1. For the specific contents of the parameter acquisition module, model building module, statistical analysis module and influencing factor determination module, please refer to the description of Example 1.

[0100] Example 3

[0101] This embodiment provides a storage medium storing a program file, wherein the program file is executed to implement the method for determining influencing factors of a high geothermal tunnel in embodiment 1.

[0102] The storage medium in this embodiment may specifically include random access memory (RAM), internal memory, read-only memory (ROM), programmable ROM, erasable programmable ROM, register, hard disk, removable disk or CD-ROM. It should be noted that those skilled in the art may specifically select the form and type of storage medium according to actual use requirements, and this embodiment does not make further specific limitations.

[0103] Example 4

[0104] This embodiment provides an electronic device, including a processor and a memory coupled to each other, wherein:

[0105] The memory is used to store the method for determining the influencing factors of the high ground temperature tunnel according to the first embodiment;

[0106] The processor is used to execute program instructions stored in the memory.

[0107] The electronic device in this embodiment includes any electronic device that can execute program instructions, such as a computer, a mobile terminal or a wearable device.

[0108] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or part or all of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the present invention.

Claims

1. A method for determining influencing factors of high ground temperature tunnels, characterized in that: The following steps are involved: S1: Obtain the maximum lining temperature and multiple influencing parameters; S2: Establish a multivariate linear regression analysis model based on the maximum lining temperature and multiple influencing parameters; S3: Calculate the standardized coefficient Beta value of the multivariate linear regression analysis model using statistical analysis software; S4: Determine the influencing factors of high ground temperature tunnels based on the standardized coefficient Beta value; Among them, Beta ≥ 0.5 is a first-level influencing factor; 0.1≤Beta<0.5, which is a secondary influencing factor; Beta<0.1, which is a third-level influencing factor.

2. The method for determining influencing factors of high ground temperature tunnels according to claim 1 is characterized in that: The step S3 specifically includes: S3.1: Use statistical analysis software to calculate the standardized coefficient Beta value and VIF value of the multivariate linear regression analysis model; If VIF≤10, there is no multicollinearity between the influencing parameters, and the process continues to step S4, where the VIF value refers to the collinearity index; If VIF>10, there is multicollinearity among the influencing parameters, and then continue with step S3.2; S3.2: Use the ridge regression analysis method to perform nonlinear optimization on each influencing parameter until VIF ≤ 10, and then continue to step S4.

3. The method for determining influencing factors of high ground temperature tunnels according to claim 2 is characterized in that: The calculation model corresponding to the ridge regression analysis method in step S2.2 is: Where X is the matrix formed by the influencing parameters; T is the transposed sign; k is the ridge parameter; I is the unit matrix; Y is the matrix formed by the maximum lining temperature; is the ridge regression estimator.

4. The method for determining influencing factors of high ground temperature tunnels according to claim 1, characterized in that: In step S2, the multivariate linear regression analysis model is: Y=β0+β1X1+β2X2+…+β m X m +e Where Y is the matrix formed by the maximum lining temperature; β0, β1, …, β m are regression coefficients; X0, X1, …, X m are the influencing parameters; ε is the random error.

5. The method for determining influencing factors of high ground temperature tunnels according to claim 1, characterized in that: The method for determining the influencing factors of the high geothermal tunnel also includes: S5: Eliminate the third-level influencing factors, take the first-level influencing factors as the main influencing factors, and take the second-level influencing factors as the secondary influencing factors.

6. The method for determining influencing factors of high ground temperature tunnels according to claim 1, characterized in that: The influencing parameters include tunnel face distance, porosity, surrounding rock thermal conductivity, surrounding rock initial temperature, wind flow temperature and / or convection heat transfer coefficient.

7. The method for determining influencing factors of high ground temperature tunnels according to claim 1, characterized in that: In step S3, the statistical analysis software is SPSS statistical analysis software.

8. A system for determining influencing factors of high geothermal tunnels, applied to the method for determining influencing factors of high geothermal tunnels according to claim 1, characterized in that: include: Parameter acquisition module: used to obtain the maximum lining temperature and multiple influencing parameters; Model building module: used to establish a multivariate linear regression analysis model based on the maximum lining temperature and multiple influencing parameters; Statistical analysis module: used to calculate the standardized coefficient Beta value of the multivariate linear regression analysis model using statistical analysis software; and an influencing factor determination module: used to determine the influencing factors of high ground temperature tunnels according to the standardized coefficient Beta value; Among them, Beta ≥ 0.5 is a first-level influencing factor; 0.1≤Beta<0.5, which is a secondary influencing factor; Beta<0.1, which is a third-level influencing factor.

9. A storage medium, characterized in that: A program file is stored, and the program file is executed to implement the method for determining the influencing factors of a high geothermal tunnel according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The invention comprises a processor and a memory coupled to each other, wherein: The memory is used to store the method for determining the influencing factors of the high ground temperature tunnel according to any one of claims 1 to 7; The processor is used to execute program instructions stored in the memory.

Images