Asymmetric Deformation Classification and Intelligent Prediction Method and Device for Soft Rock Tunnels

By acquiring cross-sectional scanning data of soft rock tunnels, determining influencing factor indicators, generating a deformation database, performing mean-variance normalization and dimensionality reduction processing, establishing a nonlinear mathematical model, and predicting the asymmetric deformation level of soft rock tunnels, this method solves the problem that traditional methods cannot effectively guide the construction of soft rock tunnels, and achieves more efficient and safer tunnel construction.

CN115860175BActive Publication Date: 2026-11-17CHINA UNIV OF GEOSCIENCES (BEIJING)
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202211313735.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-25
Publication Date
2026-11-17
Estimated Expiration
2042-10-25

AI Technical Summary

Technical Problem

Traditional tunnel deformation classification methods ignore the characteristics of uneven and asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance, reducing the accuracy and efficiency of tunnel monitoring results, and affecting the scientific nature and safety of construction.

Method used

By acquiring cross-sectional scanning data of soft rock tunnels, influencing factor indicators are determined, a deformation database is generated, mean-variance normalization and dimensionality reduction are performed, a nonlinear mathematical model is established, and the asymmetric deformation level of soft rock tunnels is predicted.

Benefits of technology

It improved the accuracy and efficiency of tunnel monitoring results, enhanced the scientific nature and safety of tunnel construction, and provided targeted construction guidance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115860175B_ABST
    Figure CN115860175B_ABST
Patent Text Reader

Abstract

This application discloses a method and apparatus for classifying and intelligently predicting asymmetric deformation of soft rock tunnels. The method includes: classifying the degree of non-uniform deformation of soft rock tunnels according to the deformation values ​​at various locations and the characteristics of tunnel cross-section deformation; performing stratified random sampling of samples from a soft rock deformation database to obtain a training set and a validation set; reducing the dimensionality of multiple influencing factors in the sample database to obtain principal component variables that meet preset conditions, generating an influence index for the asymmetric deformation level of soft rock; training the principal component variables and their corresponding asymmetric deformation levels in the training set to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables; and obtaining the final nonlinear mathematical model after validation based on the validation set, thereby obtaining the prediction result for the asymmetric deformation level of any soft rock tunnel. This application's embodiments improve the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of rock technology, and in particular to a method and device for classifying and intelligently predicting asymmetric deformation of soft rock tunnels. Background Technology

[0002] In related technologies, traditional tunnel deformation classification assesses the degree of soft rock deformation by considering the tunnel arch settlement and horizontal convergence displacement values ​​obtained from monitoring and measurement. Most traditional deformation classification predictions are based on this foundation to scientifically and effectively guide tunnel construction.

[0003] However, the relevant technologies have overlooked the characteristics of uneven and asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels. This reduces the accuracy and efficiency of tunnel monitoring results, as well as the scientific nature and safety of tunnel construction, which urgently needs to be addressed. Summary of the Invention

[0004] This application is based on the inventor's understanding and insights into the following issues:

[0005] With the rapid development of my country's economic construction and the continuous growth of transportation demand, the number of long and deep buried tunnels is increasing, and the geological conditions are becoming more and more complex. More and more railway tunnel lines will pass through soft rock strata. Soft rock tunnels are susceptible to the influence of various factors such as high ground stress, topography, geological structure, and excavation methods, which leads to differences in the strength and stress distribution of the surrounding rock on both sides of the tunnel and causes asymmetric large deformation geological disasters. The structure bears asymmetric loads and cracks are generated. Conventional support methods are difficult to meet the requirements, which brings many safety hazards to the safe construction of tunnels.

[0006] The large deformation mechanism of soft rock tunnels under high ground stress is quite complex, making it difficult to achieve a one-time and reasonable solution for large deformations in soft rock. Research on deformation classification and prediction of soft rock tunnels helps to accurately assess the degree of soft rock deformation at the construction site and scientifically and effectively guide tunnel construction. However, traditional tunnel deformation classification only considers the tunnel crown settlement and horizontal convergence displacement values ​​obtained from monitoring and measurement, which cannot reflect the overall deformation and abnormal deformation of the tunnel. Traditional deformation classification and prediction are also mostly based on this, ignoring the characteristics of uneven and asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels.

[0007] This application provides a method and device for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, in order to solve the problems in related technologies that ignore the characteristics of uneven asymmetric deformation of soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and reducing the scientific nature and safety of tunnel construction.

[0008] The first aspect of this application provides a method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, comprising the following steps: acquiring cross-sectional scanning data of the soft rock tunnel under study, and determining all influencing factor indicators for deformation classification of the soft rock tunnel based on the characteristics of soft rock, generating a soft rock deformation database; determining the difference between the tunnel cross-sectional scanning data after the initial support deformation stabilizes and the data at the initial excavation stage, obtaining the deformation values ​​at each location of the full cross-section of the target study section; classifying the degree of non-uniform deformation of the soft rock tunnel according to the characteristics of tunnel cross-sectional deformation based on the deformation values ​​at each location; and performing stratified random sampling on the samples in the soft rock deformation database. A training set and a validation set are obtained; the index values ​​in the soft rock deformation database are normalized for mean and variance to generate a normalized sample library; multiple influencing factors in the sample library are dimensionality reduced to obtain principal component variables that meet preset conditions, generating an influence index for the asymmetric deformation level of soft rock; the principal component variables and their corresponding asymmetric deformation levels in the training set are trained to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables, and after validation based on the validation set, a final nonlinear mathematical model is obtained, which is then used to predict the asymmetric deformation level of any soft rock tunnel.

[0009] Optionally, in one embodiment of this application, the step of determining all influencing factor indicators for the deformation classification of soft rock tunnels based on the characteristics of soft rock, and generating a soft rock deformation database, includes: determining influencing factor indicators for the asymmetric deformation classification of soft rock tunnels based on the deformation characteristics of the surrounding rock of the soft rock tunnel, wherein the influencing factor indicators include at least one of in-situ stress, rock unit weight, water content, elastic modulus, Poisson's ratio, cohesion, internal friction angle, and tunnel burial depth; and collecting index data of each section of the soft rock tunnel to be studied to form a soft rock deformation database of asymmetric deformation levels.

[0010] Optionally, in one embodiment of this application, the step of classifying the degree of non-uniform deformation of the soft rock tunnel based on the deformation values ​​at each location and the characteristics of tunnel cross-section deformation includes: classifying the asymmetric deformation of the soft rock tunnel according to the average deformation coefficient, the non-uniform deformation coefficient, and the abnormal deformation coefficient.

[0011] Optionally, in one embodiment of this application, the formula for calculating the average deformation coefficient is:

[0012]

[0013] Where L is the circumferential length of the tunnel (excluding the invert arch), δ(l) is the tunnel deformation function, and R is the initial radius of the tunnel.

[0014] A second aspect of this application provides a method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, comprising: obtaining principal component variables of a target soft rock tunnel; inputting the principal component variables into a pre-constructed nonlinear mathematical model, and outputting a nonlinear relationship between the principal component variables and the soft rock deformation level, wherein the nonlinear mathematical model is obtained by stratified random sampling of samples from a soft rock deformation database; and obtaining a prediction result of the asymmetric deformation level of the target soft rock tunnel based on the nonlinear relationship.

[0015] A third aspect of this application provides a device for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, comprising: a first determining module, used to acquire cross-sectional scanning data of the soft rock tunnel under study, and determine all influencing factor indicators for deformation classification of the soft rock tunnel based on the characteristics of soft rock, generating a soft rock deformation database; a second determining module, used to determine the difference between the tunnel cross-sectional scanning data after the initial support deformation stabilizes and the data at the initial excavation, obtaining the deformation values ​​at each location of the full cross-section of the target study section; a classifying module, used to classify the degree of non-uniform deformation of the soft rock tunnel according to the characteristics of tunnel cross-sectional deformation based on the deformation values ​​at each location; and a first generating module, used to stratify the soft rock deformation database samples. Random sampling is used to obtain training and validation sets. A processing module performs mean and variance normalization on the index values ​​in the soft rock deformation database to generate a normalized sample library. A second generation module performs dimensionality reduction on multiple influencing factors in the sample library to obtain principal component variables that meet preset conditions, generating an influence index for the asymmetric deformation level of soft rock. A prediction module trains the principal component variables and their corresponding asymmetric deformation levels in the training set to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables. After validation based on the validation set, a final nonlinear mathematical model is obtained, which is then used to predict the asymmetric deformation level of any soft rock tunnel.

[0016] Optionally, in one embodiment of this application, the first determining module includes: a determining unit, used to determine the influencing factor indexes for the asymmetric deformation classification of soft rock tunnels based on the deformation characteristics of the surrounding rock, wherein the influencing factor indexes include at least one of in-situ stress, rock unit weight, water content, elastic modulus, Poisson's ratio, cohesion, internal friction angle, and tunnel burial depth; and a generating unit, used to collect index data of each section of the soft rock tunnel under study to form a soft rock deformation database of asymmetric deformation levels. Optionally, in one embodiment of this application, the classification module is further used to classify the asymmetric deformation of the soft rock tunnel into deformation levels based on the average deformation coefficient, the uneven deformation coefficient, and the abnormal deformation coefficient.

[0017] Optionally, in one embodiment of this application, the formula for calculating the average deformation coefficient is:

[0018]

[0019] Where L is the circumferential length of the tunnel (excluding the invert arch), δ(l) is the tunnel deformation function, and R is the initial radius of the tunnel.

[0020] A fourth aspect of this application provides a device for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, comprising: an acquisition module for acquiring principal component variables of a target soft rock tunnel; a control module for inputting the principal component variables into a pre-constructed nonlinear mathematical model and outputting a nonlinear relationship between the principal component variables and the soft rock deformation level, wherein the nonlinear mathematical model is obtained by stratified random sampling from a soft rock deformation database sample; and a generation module for obtaining a predicted result of the asymmetric deformation level of the target soft rock tunnel based on the nonlinear relationship.

[0021] A fifth aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the asymmetric deformation grading and intelligent prediction method for soft rock tunnels as described in the above embodiments.

[0022] A sixth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels.

[0023] This application's embodiments can classify the degree of non-uniform deformation of soft rock tunnels based on deformation values ​​at various locations and the characteristics of tunnel cross-section deformation. It performs stratified random sampling of the soft rock deformation database samples to obtain training and validation sets. Dimensionality reduction is applied to multiple influencing factors in the sample database to obtain principal component variables that meet preset conditions, generating an influence index for the asymmetric deformation level of soft rock. The principal component variables and corresponding asymmetric deformation levels in the training set are then used to train a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables. After validation based on the validation set, the final nonlinear mathematical model is obtained, thus providing a prediction result for the asymmetric deformation level of any soft rock tunnel. This improves the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction. Therefore, it solves the problems in related technologies that ignore the characteristics of non-uniform and asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and lowering the scientific nature and safety of tunnel construction.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0026] Figure 1 This is a flowchart of a method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels according to an embodiment of this application;

[0027] Figure 2 A flowchart of a specific embodiment of the method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels according to this application;

[0028] Figure 3 This is a flowchart of another method for asymmetric deformation classification and intelligent prediction of soft rock tunnels according to an embodiment of this application;

[0029] Figure 4 This is a schematic diagram of the structure of the asymmetric deformation classification and intelligent prediction device for soft rock tunnels according to an embodiment of this application;

[0030] Figure 5 This is a schematic diagram of another asymmetric deformation classification and intelligent prediction device for soft rock tunnels according to an embodiment of this application;

[0031] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0033] The following describes, with reference to the accompanying drawings, a method and apparatus for classifying and intelligently predicting asymmetric deformation of soft rock tunnels according to embodiments of this application. To address the issue that the aforementioned related technologies neglect the characteristics of uneven and asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels and reducing the accuracy and efficiency of tunnel monitoring results, as well as the scientific and safety aspects of tunnel construction, this application provides a method for classifying and intelligently predicting asymmetric deformation in soft rock tunnels. This method classifies the degree of uneven deformation in soft rock tunnels based on deformation values ​​at various locations and the characteristics of tunnel cross-section deformation. It performs stratified random sampling of the soft rock deformation database samples to obtain training and validation sets. Dimensionality reduction is applied to multiple influencing factors in the sample database to obtain principal component variables that meet preset conditions, generating an influence index for the asymmetric deformation level of soft rock. The principal component variables and corresponding asymmetric deformation levels in the training set are then used to train a nonlinear mathematical model between the asymmetric deformation level and the principal component variables. After validation on the validation set, the final nonlinear mathematical model is obtained, thus predicting the asymmetric deformation level of any soft rock tunnel. This improves the accuracy and efficiency of tunnel monitoring results while enhancing the scientific and safety aspects of tunnel construction. This solves the problems in related technologies that ignore the characteristics of uneven and asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and lowering the scientific nature and safety of tunnel construction.

[0034] Specifically, Figure 1 This is a flowchart illustrating a method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, as provided in an embodiment of this application.

[0035] like Figure 1 As shown, the asymmetric deformation classification and intelligent prediction method for soft rock tunnels includes the following steps:

[0036] In step S101, cross-sectional scanning data of the soft rock tunnel to be studied is obtained, and all influencing factor indicators for the deformation classification of soft rock tunnels are determined based on the characteristics of soft rock, generating a soft rock deformation database.

[0037] It is understood that the embodiments of this application can obtain cross-sectional scanning data of the soft rock tunnel to be studied, and determine all the influencing factor indicators of the deformation classification of the soft rock tunnel based on the characteristics of the soft rock in the following steps, thereby generating a soft rock deformation database, thereby effectively improving the accuracy of the data and enhancing the intelligence of tunnel monitoring.

[0038] In one embodiment of this application, based on the characteristics of soft rock, all influencing factor indicators for the deformation classification of soft rock tunnels are determined, and a soft rock deformation database is generated. This includes: determining the influencing factor indicators for the asymmetric deformation classification of soft rock tunnels based on the deformation characteristics of the surrounding rock of the soft rock tunnels, wherein the influencing factor indicators include at least one of in-situ stress, rock unit weight, water content, elastic modulus, Poisson's ratio, cohesion, internal friction angle, and tunnel burial depth; collecting index data of each section of the soft rock tunnel to be studied to form a soft rock deformation database of asymmetric deformation levels.

[0039] For example, this application embodiment can determine the influencing factor index y of asymmetric deformation classification of soft rock tunnels based on the deformation characteristics of the surrounding rock. The influencing factor index includes, but is not limited to, ground stress x1, rock unit weight x2, water content x3, elastic modulus x4, Poisson's ratio x5, cohesion x6, internal friction angle x7, and tunnel burial depth x8. The index data of each section of the target soft rock tunnel are collected to form an index database of asymmetric deformation level of soft rock, thereby effectively improving the accuracy of the data and the efficiency and accuracy of the prediction results.

[0040] In step S102, the difference between the tunnel cross-section scanning data after the initial support deformation stabilizes and the initial tunnel excavation is determined to obtain the deformation value at each location of the entire cross-section of the target study section.

[0041] It is understood that, based on the characteristics of uneven and asymmetric deformation that easily occurs in soft rock tunnels, the embodiments of this application can improve the method of monitoring and measuring to obtain tunnel deformation data. The contour of the tunnel cross section can be obtained by multiple cross-sectional scans. Based on the difference between the tunnel cross-sectional scan data after the initial support deformation stabilizes and the data after the initial excavation, the deformation values ​​at each position of the target study section can be obtained. This allows for a more comprehensive and complete acquisition of the uneven deformation at each position of the soft rock tunnel cross section, which is beneficial for the classification of asymmetric deformation in soft rock.

[0042] In step S103, based on the deformation values ​​at each location, the degree of non-uniform deformation of the soft rock tunnel is classified according to the characteristics of the tunnel cross-section deformation.

[0043] It is understood that, after obtaining the cross-sectional deformation data of the soft rock tunnel, the embodiments of this application can classify the degree of non-uniform deformation of the soft rock tunnel according to the characteristics of the tunnel cross-sectional deformation, thereby more comprehensively and accurately describing the asymmetric deformation of the soft rock tunnel, and making it more detailed and practical.

[0044] In one embodiment of this application, the degree of non-uniform deformation of soft rock tunnels is classified according to the deformation values ​​at each location and the characteristics of tunnel cross-section deformation. This includes classifying the asymmetric deformation of soft rock tunnels according to the average deformation coefficient, the non-uniform deformation coefficient, and the abnormal deformation coefficient.

[0045] For example, in the embodiments of this application, after obtaining the cross-sectional deformation data of a soft rock tunnel, the average deformation coefficient can be used to determine the deformation. The uneven deformation coefficient ξ and the abnormal deformation coefficient λ are used to classify the deformation level of the asymmetric deformation of soft rock tunnels.

[0046] Among them, the average deformation coefficient The formula is shown below:

[0047]

[0048] Where L is the circumferential length of the tunnel (excluding the invert arch), δ(l) is the tunnel deformation function, which represents the distance between the actual tunnel cross-section and the initial cross-section at the corresponding location, and R is the initial radius of the tunnel.

[0049] The formula for the coefficient of uneven deformation ξ is as follows:

[0050]

[0051] Among them, S 侵 S represents the encroachment area of ​​the cross section. 扩 n1 is the area of ​​the cross-section expansion, and l is the number of encroachment areas of the cross-section. n1 Let δ1(l) be the arc length of the encroached portion of the cross-section, δ1(l) be the deformation function of the encroached portion of the cross-section, representing the distance between the actual cross-section of the tunnel and the designed cross-section at the corresponding location, and n2 be the number of outward expansion areas of the cross-section. n2 Let δ2(l) be the arc length of the outer portion of the cross-section, and let δ2(l) be the deformation function of the outer portion of the cross-section, representing the distance between the actual cross-section of the tunnel and the designed cross-section at the corresponding location.

[0052] The formula for the abnormal deformation coefficient λ is as follows:

[0053]

[0054] Furthermore, in the embodiments of this application, the average deformation coefficient can be calculated based on existing research and the characteristics of soft rock tunnel engineering. After determining the uneven deformation coefficient ξ and the abnormal deformation coefficient λ, the degree of deformation for each index is divided into five levels, from I to V. Table 1 is the grading table for the average deformation coefficient, Table 2 is the grading table for the uneven deformation coefficient, and Table 3 is the grading table for the abnormal deformation coefficient. The specific tables 1, 2, and 3 are shown below:

[0055] Table 1

[0056]

[0057] Table 2

[0058]

[0059] Table 3

[0060]

[0061] In summary, the embodiments of this application can classify soft rock deformation using three indicators, among which the average deformation coefficient... The magnitude of the coefficient of variation can provide a reference for determining and optimizing tunnel excavation methods and support strength. The magnitude of the coefficient of variation ξ can provide a reference for determining the support methods and strength for tunnels with uneven deformation. The magnitude of the coefficient of abnormal deformation λ can measure the degree of abnormal deformation development in the encroachment area, thereby determining the strength of local reinforcement support. It can also more comprehensively and accurately describe the asymmetric deformation of soft rock tunnels, making it accurate, efficient, convenient and practical.

[0062] In step S104, stratified random sampling is performed on the soft rock deformation database samples to obtain the training set and the validation set.

[0063] It is understood that the embodiments of this application can perform stratified random sampling on samples from the soft rock deformation database to obtain training and validation sets. For example, 80% of the samples can be used as the training set to obtain a stable model, and 20% of the samples can be used as the validation set to test the generalization ability of the model. Among them, the stratified sampling method for establishing training and validation sample sets, compared with simple random sampling and equidistant random sampling, has a smaller sampling error when the number of samples is the same, requires fewer samples when the sampling error requirement is the same, and the samples obtained by sampling are more representative, safe, efficient and convenient.

[0064] As one possible approach, when obtaining the non-uniform deformation levels and corresponding influencing factor samples of each section of a soft rock tunnel, this embodiment of the application can provide training data for establishing a non-linear model between the non-uniform deformation levels and influencing factors. For example, this embodiment of the application can use a stratified sampling method to randomly select samples from different layers as training sets at a ratio of 80%, and the remaining 20% ​​as validation data samples for training the model. Each sample contains 8 influencing factor indicators (ground stress x1, rock unit weight x2, water content x3, elastic modulus x4, Poisson's ratio x5, cohesion x6, internal friction angle x7, and tunnel burial depth x8) and 3 deformation levels (average deformation level y1, non-uniform deformation level y2, and abnormal deformation level y3).

[0065] In step S105, the index values ​​in the soft rock deformation database are normalized by mean and variance to generate a normalized sample library.

[0066] It is understood that the embodiments of this application can perform mean and variance normalization processing on the index values ​​in the soft rock deformation database to generate a normalized sample library, which can effectively reduce the errors caused by data with large range differences, avoid the influence of differences in the dimensions of various indices, and provide better data support for establishing the nonlinear relationship between the asymmetric deformation level of soft rock and various influencing factors.

[0067] For example, in order to eliminate the differences in the dimensions and ranges of various influencing factors, the original index data x1, x2, x3, x4, x5, x6, x7 and x8 of non-uniform asymmetric deformation of soft rock tunnels can be normalized for mean and variance according to the following formula.

[0068] Among them, the normalized index value for:

[0069]

[0070] in, The normalized index value, s j Let be the standard deviation of the j-th indicator.

[0071] The average value of the j-th indicator for:

[0072]

[0073] in, Let be the average value of the j-th indicator.

[0074] The standard deviation of the j-th indicator s j for:

[0075]

[0076] in, Let s be the average value of the j-th indicator. j Let be the standard deviation of the j-th indicator.

[0077] In step S106, multiple influencing factors in the sample library are dimensionality reduced to obtain principal component variables that meet preset conditions, and an influence index for the asymmetric deformation level of soft rock is generated.

[0078] It is understood that the embodiments of this application can reduce the dimensionality of multiple influencing factors in the sample library to obtain principal component variables that meet certain conditions, and generate an influencing index of the asymmetric deformation level of soft rock. For example, principal component analysis can be used to reduce the dimensionality of multiple normalized index data, and the top k principal components with eigenvalues ​​greater than 1 and cumulative variance contribution rates of 85% to 95% can be taken as new influencing factors of uneven asymmetric deformation of soft rock tunnels.

[0079] Therefore, the embodiments of this application can indirectly predict the asymmetric deformation level of soft rock tunnels by reducing the dimensionality of each influencing factor index through principal component analysis, thereby reducing the number of influencing factors, reducing the input dimension of the model, and using low-dimensional input variables to build a neural network model, which can effectively reduce the complexity of the model and the computational complexity.

[0080] It should be noted that the preset conditions are set by those skilled in the art based on the actual situation, and no specific limitations are made here.

[0081] In step S107, the principal component variables and their corresponding asymmetric deformation levels in the training set are trained to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables. After verification based on the validation set, the final nonlinear mathematical model is obtained, and the asymmetric deformation level prediction result of any soft rock tunnel is obtained using the final nonlinear mathematical model.

[0082] It is understood that the embodiments of this application can train the principal component variables and their corresponding asymmetric deformation levels in the training set. For example, a BP neural network can be used to train the principal component variables and their corresponding asymmetric deformation levels in the training set to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables. After verification based on the validation set, the final nonlinear mathematical model is obtained. The final nonlinear mathematical model can be used to obtain the prediction result of the asymmetric deformation level of any soft rock tunnel, thereby effectively improving the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction.

[0083] For example, embodiments of this application can establish principal component variables (x'1, x'2, ..., x') in the training data based on a BP neural network with k inputs and 3 outputs. k A nonlinear model is used to describe the highly complex nonlinear relationship between principal component variables and soft rock deformation levels (average deformation level y1, uneven deformation level y2, and abnormal deformation level y3) of soft rock tunnels.

[0084] Next, in this embodiment of the application, 20% of the validation data can be used to perform validation calculations on the established neural network model to verify the accuracy and generalization ability of the established nonlinear model, providing technical support for subsequent engineering applications.

[0085] like Figure 2 As shown, the working principle of the embodiments of this application will be described in detail below with a specific example.

[0086] Step S201: Asymmetric deformation classification and prediction of soft rock tunnels, followed by steps S202 and S205 respectively.

[0087] Step S202: Obtain cross-sectional scanning data of soft rock, that is, obtain cross-sectional scanning data of the soft rock tunnel under study.

[0088] Step S203: Subtract the scan data of the same cross section to obtain the overall deformation value of the cross section.

[0089] Step S204: Classify the asymmetric deformation of soft rock according to the average deformation coefficient, the uneven deformation coefficient, and the abnormal deformation coefficient.

[0090] Step S205: Determine the influencing factor indicators.

[0091] Step S206: Collect image factor indicators of each section of the soft rock tunnel, that is, determine all the influencing factor indicators of the deformation classification of the soft rock tunnel based on the characteristics of soft rock.

[0092] Step S207: Database of asymmetric deformation of soft rock tunnels.

[0093] Step S208: Prediction of asymmetric deformation level of soft rock tunnel.

[0094] Step S209: Normalize the mean and variance of the image factors, perform principal component analysis to reduce the dimensionality and obtain k principal component variables, and then execute steps S210 and S211 respectively.

[0095] Step S210: 80% training set, that is, stratified random sampling of samples from the soft rock deformation database, wherein 80% of the samples are used as the training set to obtain a stable model, and the principal component variables and corresponding asymmetric deformation levels in the training set are trained.

[0096] Step S211: 20% validation set, which is to perform stratified random sampling on the soft rock deformation database samples, of which 20% of the samples are used as the validation set to test the generalization ability of the model, and after validation based on the validation set, the final nonlinear mathematical model is obtained.

[0097] Step S212: The new engineering data undergoes the same principal component dimensionality reduction, that is, multiple influencing factors in the sample library are reduced in dimensionality to obtain principal component variables that meet the conditions, and the influencing index of the asymmetric deformation level of soft rock is generated.

[0098] Step S213: Asymmetric deformation level of soft rock, that is, using the final nonlinear mathematical model to obtain the prediction result of the asymmetric deformation level of any soft rock tunnel, thereby improving the accuracy and intelligence of tunnel monitoring results.

[0099] The method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels according to the embodiments of this application can classify the degree of non-uniform deformation of soft rock tunnels based on the deformation values ​​at various locations and the characteristics of tunnel cross-section deformation. It performs stratified random sampling of the soft rock deformation database samples to obtain training and validation sets. Multiple influencing factors in the sample database are dimensionality-reduced to obtain principal component variables that meet preset conditions, generating influence indicators for the asymmetric deformation level of soft rock. The principal component variables and corresponding asymmetric deformation levels in the training set are then trained to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables. After validation based on the validation set, the final nonlinear mathematical model is obtained, thus obtaining the prediction result of the asymmetric deformation level of any soft rock tunnel. This improves the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction. Therefore, it solves the problems in related technologies that ignore the characteristics of non-uniform asymmetric deformation of soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and lowering the scientific nature and safety of tunnel construction.

[0100] then, Figure 3 This is a flowchart illustrating another method for asymmetric deformation classification and intelligent prediction of soft rock tunnels provided in an embodiment of this application.

[0101] like Figure 3 As shown, the asymmetric deformation classification and intelligent prediction method for soft rock tunnels includes the following steps:

[0102] In step S301, the principal component variables of the target soft rock tunnel are obtained.

[0103] It is understood that the embodiments of this application can obtain the principal component variables of the target soft rock tunnel. For example, the values ​​of eight influencing factors near the working face of an unexcavated soft rock tunnel can be obtained as a test set using relevant methods. The relevant methods are not specifically limited here. The principal component variables of the test set are obtained based on the average value and standard deviation of the database indicators, which can then be substituted into the nonlinear mathematical model pre-built in the following steps to improve the efficiency and accuracy of the prediction.

[0104] In step S302, the principal component variables are input into a pre-constructed nonlinear mathematical model, and the nonlinear relationship between the principal component variables and the soft rock deformation level is output. The nonlinear mathematical model is obtained by stratified random sampling of samples from the soft rock deformation database.

[0105] It is understood that the embodiments of this application can input the principal component variables calculated in the above steps into a pre-constructed nonlinear mathematical model and output the nonlinear relationship between the principal component variables and the soft rock deformation level. The nonlinear mathematical model is obtained by stratified random sampling of samples from the soft rock deformation database, thereby effectively improving the accuracy of the prediction results.

[0106] In step S303, the asymmetric deformation level prediction result of the target soft rock tunnel is obtained based on the nonlinear relationship.

[0107] It is understood that the embodiments of this application can input the principal component variables of the target soft rock tunnel into the established and verified mathematical model, output the nonlinear relationship between the principal component variables and the soft rock deformation level, and predict the asymmetric deformation level of the soft rock tunnel. Thus, the asymmetric deformation level prediction result of the target soft rock tunnel can be obtained based on the nonlinear relationship, which can effectively guide the safe construction of soft rock tunnels.

[0108] In summary, the embodiments of this application can be effectively applied to engineering practice. By normalizing the mean and variance of the test data at the engineering site based on the mean and variance of the indicators in the database, and then substituting the data into the trained and verified nonlinear mathematical model after dimensionality reduction by principal component analysis, the asymmetric deformation level of soft rock tunnels can be predicted. Moreover, the prediction results more comprehensively show the overall deformation overview of soft rock tunnels. Furthermore, it integrates the asymmetric deformation classification and level prediction of soft rock tunnels into one method. The method is simple and the process is coherent, which can provide targeted guidance for the construction of soft rock tunnels and improve the safety of soft rock tunnel construction.

[0109] The method for asymmetric deformation classification and intelligent prediction of soft rock tunnels proposed in this application can obtain the principal component variables of the target soft rock tunnel, input the principal component variables into a pre-constructed nonlinear mathematical model, and output the nonlinear relationship between the principal component variables and the soft rock deformation level. The nonlinear mathematical model is obtained by stratified random sampling from a soft rock deformation database sample. Based on the nonlinear relationship, the asymmetric deformation level prediction result of the target soft rock tunnel is obtained, thereby improving the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction. This solves the problems in related technologies that ignore the characteristics of uneven asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and lowering the scientific nature and safety of tunnel construction.

[0110] Next, referring to the accompanying drawings, the asymmetric deformation classification and intelligent prediction device for soft rock tunnels proposed according to the embodiments of this application is described.

[0111] Figure 4 This is a block diagram of the asymmetric deformation classification and intelligent prediction device for soft rock tunnels according to an embodiment of this application.

[0112] like Figure 4 As shown, the asymmetric deformation classification and intelligent prediction device 10 for soft rock tunnels includes: a first determination module 100, a second determination module 200, a classification module 300, a first generation module 400, a processing module 500, a second generation module 600, and a prediction module 700.

[0113] Specifically, the first determining module 100 is used to acquire cross-sectional scanning data of the soft rock tunnel to be studied, and to determine all the influencing factor indicators of the deformation classification of the soft rock tunnel based on the characteristics of the soft rock, and generate a soft rock deformation database.

[0114] The second determining module 200 is used to determine the difference between the tunnel cross-section scanning data after the initial support deformation stabilizes and the initial tunnel excavation, so as to obtain the deformation value at each position of the entire cross-section of the target study section.

[0115] The grading module 300 is used to grade the degree of non-uniform deformation of soft rock tunnels based on the deformation values ​​at each location and the characteristics of tunnel cross-section deformation.

[0116] The first generation module 400 is used to perform stratified random sampling on samples from the soft rock deformation database to obtain training and validation sets.

[0117] The processing module 500 is used to perform mean and variance normalization on the index values ​​in the soft rock deformation database to generate a normalized sample library.

[0118] The second generation module 600 is used to reduce the dimensionality of multiple influencing factors in the sample library, obtain principal component variables that meet preset conditions, and generate the influence index of the asymmetric deformation level of soft rock.

[0119] The prediction module 700 is used to train the principal component variables and their corresponding asymmetric deformation levels in the training set, establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables, and obtain the final nonlinear mathematical model after validation based on the validation set, so as to obtain the prediction result of the asymmetric deformation level of any soft rock tunnel using the final nonlinear mathematical model.

[0120] Optionally, in one embodiment of this application, the first determining module 100 includes a determining unit and a generating unit.

[0121] The "determining unit" is used to determine the influencing factors of asymmetric deformation classification of soft rock tunnels based on the deformation characteristics of the surrounding rock. The influencing factors include at least one of the following: ground stress, rock unit weight, water content, elastic modulus, Poisson's ratio, cohesion, internal friction angle, and tunnel burial depth.

[0122] The generation unit is used to collect index data of each section of the soft rock tunnel to be studied, and form a soft rock deformation database of asymmetric deformation levels.

[0123] Optionally, in one embodiment of this application, the classification module 300 is further used to classify the asymmetric deformation of soft rock tunnels according to the average deformation coefficient, the uneven deformation coefficient, and the abnormal deformation coefficient.

[0124] Optionally, in one embodiment of this application, the formula for calculating the average deformation coefficient is:

[0125]

[0126] Where L is the circumferential length of the tunnel (excluding the invert arch), δ(l) is the tunnel deformation function, and R is the initial radius of the tunnel.

[0127] It should be noted that the foregoing explanation of the embodiment of the asymmetric deformation classification and intelligent prediction method for soft rock tunnels also applies to the asymmetric deformation classification and intelligent prediction device for soft rock tunnels in this embodiment, and will not be repeated here.

[0128] The asymmetric deformation grading and intelligent prediction device for soft rock tunnels proposed in this application can classify the degree of non-uniform deformation of soft rock tunnels based on deformation values ​​at various locations and the characteristics of tunnel cross-section deformation. It performs stratified random sampling of the soft rock deformation database samples to obtain training and validation sets. Multiple influencing factors in the sample database are dimensionality-reduced to obtain principal component variables that meet preset conditions, generating influence indicators for the asymmetric deformation level of soft rock. The principal component variables and corresponding asymmetric deformation levels in the training set are then trained to establish a nonlinear mathematical model between the asymmetric deformation level and the principal component variables. After validation based on the validation set, the final nonlinear mathematical model is obtained, thus predicting the asymmetric deformation level of any soft rock tunnel. This improves the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction. Therefore, it solves the problems in related technologies that ignore the characteristics of non-uniform asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and lowering the scientific nature and safety of tunnel construction.

[0129] Next, with reference to the accompanying drawings, another asymmetric deformation classification and intelligent prediction device for soft rock tunnels according to an embodiment of this application will be described.

[0130] Figure 5 This is a block diagram of the asymmetric deformation classification and intelligent prediction device for soft rock tunnels according to an embodiment of this application.

[0131] like Figure 5As shown, the asymmetric deformation classification and intelligent prediction device 20 for soft rock tunnels includes: an acquisition module 800, a control module 900, and a generation module 1000.

[0132] Specifically, module 800 is used to obtain the principal component variables of the target soft rock tunnel.

[0133] The control module 900 is used to input the principal component variables into a pre-built nonlinear mathematical model and output the nonlinear relationship between the principal component variables and the soft rock deformation level. The nonlinear mathematical model is obtained by stratified random sampling of samples from the soft rock deformation database.

[0134] The generation module 1000 is used to obtain the prediction results of the asymmetric deformation level of the target soft rock tunnel based on the nonlinear relationship.

[0135] It should be noted that the foregoing explanation of the embodiment of the asymmetric deformation classification and intelligent prediction method for soft rock tunnels also applies to the asymmetric deformation classification and intelligent prediction device for soft rock tunnels in this embodiment, and will not be repeated here.

[0136] The asymmetric deformation grading and intelligent prediction device for soft rock tunnels proposed in this application can acquire the principal component variables of the target soft rock tunnel, input the principal component variables into a pre-constructed nonlinear mathematical model, and output the nonlinear relationship between the principal component variables and the soft rock deformation level. The nonlinear mathematical model is obtained by stratified random sampling from a soft rock deformation database sample. Based on the nonlinear relationship, the asymmetric deformation level prediction result of the target soft rock tunnel is obtained, thereby improving the accuracy and efficiency of tunnel monitoring results while enhancing the scientific nature and safety of tunnel construction. This solves the problems in related technologies that ignore the characteristics of uneven asymmetric deformation in soft rock tunnels, making it difficult to provide targeted construction guidance for soft rock tunnels, reducing the accuracy and efficiency of tunnel monitoring results, and lowering the scientific nature and safety of tunnel construction.

[0137] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0138] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0139] When the processor 602 executes the program, it implements the asymmetric deformation classification and intelligent prediction method for soft rock tunnels provided in the above embodiments.

[0140] Furthermore, electronic devices also include:

[0141] Communication interface 603 is used for communication between memory 601 and processor 602.

[0142] The memory 601 is used to store computer programs that can run on the processor 602.

[0143] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0144] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0145] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0146] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0147] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-mentioned method for asymmetric deformation classification and intelligent prediction of soft rock tunnels.

[0148] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0149] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0150] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0151] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0152] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0153] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0154] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0155] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, characterized in that, Includes the following steps: Obtain cross-sectional scanning data of the soft rock tunnel to be studied, and determine all the influencing factors of soft rock tunnel deformation classification based on the characteristics of soft rock, and generate a soft rock deformation database. The difference between the initial support deformation stabilization data and the tunnel cross-section scanning data at the initial excavation is used to obtain the deformation values ​​at various locations across the entire cross-section of the target study section. Based on the deformation values ​​at each location, the degree of non-uniform deformation of soft rock tunnels is classified according to the characteristics of tunnel cross-section deformation. Stratified random sampling is performed on the soft rock deformation database samples to obtain training set and validation set; The index values ​​in the soft rock deformation database are normalized by mean and variance to generate a normalized sample library. Dimensionality reduction is performed on multiple influencing factors in the sample library to obtain principal component variables that meet preset conditions, and an influence index for the asymmetric deformation level of soft rock is generated. as well as The principal component variables and their corresponding asymmetric deformation levels in the training set are trained to establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables. After verification based on the validation set, the final nonlinear mathematical model is obtained, and the asymmetric deformation level prediction result of any soft rock tunnel is obtained using the final nonlinear mathematical model. in, The classification of the degree of non-uniform deformation of soft rock tunnels based on the deformation values ​​at each location and the characteristics of tunnel cross-section deformation includes: The asymmetric deformation of the soft rock tunnel is classified into deformation levels based on the average deformation coefficient, the uneven deformation coefficient, and the abnormal deformation coefficient. The formula for calculating the abnormal deformation coefficient is: ; The formula for calculating the average deformation coefficient is as follows: , in, L This is the circumferential length of the tunnel. δ(l) For tunnel deformation function, R The initial radius of the tunnel; The formula for calculating the coefficient of uneven deformation is as follows: in, The encroachment area is the cross-sectional area. For the area of ​​the cross-section expansion, n 1 represents the number of encroachment zones in the cross-section. l n1 The arc length of the section encroaching on the boundary. The deformation function for the encroached portion of the cross-section represents the distance between the actual tunnel cross-section and the designed cross-section at the corresponding location. n 2 represents the number of areas extending beyond the cross-section. l n2 The arc length of the outer portion of the cross-section. The deformation function for the outward expansion of the cross-section represents the distance between the actual cross-section of the tunnel and the designed cross-section at the corresponding location.

2. The method according to claim 1, characterized in that, The method involves determining all influencing factors for the deformation classification of tunnels constructed in soft rock based on the characteristics of soft rock, and generating a soft rock deformation database, including: Based on the deformation characteristics of the surrounding rock of soft rock tunnels, the influencing factors for the classification of asymmetric deformation of soft rock tunnels are determined. The influencing factors include at least one of the following: ground stress, rock unit weight, water content, elastic modulus, Poisson's ratio, cohesion, internal friction angle and tunnel burial depth. Collect index data of each section of the soft rock tunnel to be studied to form a soft rock deformation database of asymmetric deformation levels.

3. A device for classifying and intelligently predicting asymmetric deformation of soft rock tunnels, characterized in that, include: The first determination module is used to acquire cross-sectional scanning data of the soft rock tunnel to be studied, and to determine all the influencing factors of the deformation classification of the soft rock tunnel based on the characteristics of soft rock, and generate a soft rock deformation database. The second determining module is used to determine the difference between the tunnel cross-section scanning data after the initial support deformation stabilizes and the initial excavation of the tunnel, so as to obtain the deformation value at each position of the entire cross-section of the target study section. The grading module is used to classify the degree of non-uniform deformation of soft rock tunnels based on the deformation values ​​at each location and the characteristics of tunnel cross-section deformation. The first generation module is used to perform stratified random sampling on the soft rock deformation database samples to obtain a training set and a validation set. The processing module is used to perform mean and variance normalization processing on the index values ​​in the soft rock deformation database to generate a normalized sample library. The second generation module is used to reduce the dimensionality of multiple influencing factors in the sample library to obtain principal component variables that meet preset conditions, and generate an influence index of the asymmetric deformation level of soft rock. as well as The prediction module is used to train the principal component variables and their corresponding asymmetric deformation levels in the training set, establish a nonlinear mathematical model between the asymmetric deformation level of soft rock and the principal component variables, and obtain the final nonlinear mathematical model after verification based on the validation set, so as to obtain the prediction result of the asymmetric deformation level of any soft rock tunnel using the final nonlinear mathematical model. in, The grading module is used to grade the degree of non-uniform deformation of soft rock tunnels based on the deformation values ​​at each location and the characteristics of tunnel cross-section deformation. Specifically, it is used for: The asymmetric deformation of the soft rock tunnel is classified into deformation levels based on the average deformation coefficient, the uneven deformation coefficient, and the abnormal deformation coefficient. The formula for calculating the abnormal deformation coefficient in the grading module is as follows: ; The formula for calculating the average deformation coefficient is as follows: , in, L This is the circumferential length of the tunnel. δ(l) For tunnel deformation function, R The initial radius of the tunnel; The formula for calculating the coefficient of uneven deformation is as follows: in, The encroachment area is the cross-sectional area. For the area of ​​the cross-section expansion, n 1 represents the number of encroachment zones in the cross-section. l n1 The arc length of the section encroaching on the boundary. The deformation function for the encroached portion of the cross-section represents the distance between the actual tunnel cross-section and the designed cross-section at the corresponding location. n 2 represents the number of areas extending beyond the cross-section. l n2 The arc length of the outer portion of the cross-section. The deformation function for the outward expansion of the cross-section represents the distance between the actual cross-section of the tunnel and the designed cross-section at the corresponding location.

4. The apparatus according to claim 3, characterized in that, The first determining module includes: The determination unit is used to determine the influencing factor index of asymmetric deformation classification of soft rock tunnels based on the deformation characteristics of the surrounding rock. The influencing factor index includes at least one of the following: ground stress, rock unit weight, water content, elastic modulus, Poisson's ratio, cohesion, internal friction angle and tunnel burial depth. The generation unit is used to collect index data of each section of the soft rock tunnel to be studied, and form a soft rock deformation database of asymmetric deformation levels.

5. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for asymmetric deformation classification and intelligent prediction of soft rock tunnels as described in any one of claims 1-2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for classifying and intelligently predicting asymmetric deformation of soft rock tunnels as described in any one of claims 1-2.

Citation Information

Patent Citations

  • Modeling and analysis method and device for predicting tunnel extrusion deformation, and storage medium

    CN107908915A