CN114491735A - Bias multi-arch tunnel reliability evaluation method - Google Patents

Bias multi-arch tunnel reliability evaluation method Download PDF

Info

Publication number
CN114491735A
CN114491735A CN202111645505.XA CN202111645505A CN114491735A CN 114491735 A CN114491735 A CN 114491735A CN 202111645505 A CN202111645505 A CN 202111645505A CN 114491735 A CN114491735 A CN 114491735A
Authority
CN
China
Prior art keywords
arch tunnel
surrounding rock
adopting
parameter
fitting model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111645505.XA
Other languages
Chinese (zh)
Inventor
傅建红
牛海波
王正军
许建聪
肖珊珊
彭军安
鲍春钱
孟帅
沈琦
颜海伟
麻桢凯
王强
张智华
徐格格
梁艳
杨成斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Communications Construction Hongtu Traffic Construction Co ltd
Tongji University
Original Assignee
Zhejiang Communications Construction Hongtu Traffic Construction Co ltd
Tongji University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Communications Construction Hongtu Traffic Construction Co ltd, Tongji University filed Critical Zhejiang Communications Construction Hongtu Traffic Construction Co ltd
Priority to CN202111645505.XA priority Critical patent/CN114491735A/en
Publication of CN114491735A publication Critical patent/CN114491735A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Architecture (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Excavating Of Shafts Or Tunnels (AREA)

Abstract

The invention relates to a method for evaluating reliability of a bias multi-arch tunnel, which comprises the following steps: generating a specified number of parameter data sets by adopting a random uniform sampling method, and determining a numerical test scheme; according to the determined numerical test scheme, carrying out numerical simulation calculation by adopting ANSYS finite element software to obtain the displacement of the specified measuring point, and combining a parameter data set to obtain an integral parameter-displacement data set; based on the GBDT algorithm, constructing a fitting model of parameters and displacement, and selecting an optimal hyper-parameter combination by adopting a Bayesian algorithm to obtain an optimal fitting model; according to the reserved deformation value around the bias multi-arch tunnel, combining with an optimal fitting model, and inverting the surrounding rock parameters to be solved by adopting an NSGA-II algorithm to obtain optimized surrounding rock mechanical parameters; and calculating to obtain the corresponding reliable index of the primary support structure of the bias multi-arch tunnel according to the optimized mechanical parameters of the surrounding rock. Compared with the prior art, the method can simultaneously consider the function requirements of the hole periphery reserved deformation values of a plurality of measuring points, and has the advantages of high precision and high accuracy.

Description

Bias multi-arch tunnel reliability evaluation method
Technical Field
The invention relates to tunnel engineering, in particular to a bias multi-arch tunnel reliability evaluation method.
Background
With the rapid development of highway construction in China, the multi-arch tunnel is more and more widely adopted as a special tunnel structural form and is influenced by terrain and route selection, most of the multi-arch tunnels have the shallow-buried bias voltage problem, and the multi-arch tunnel is complex in structure and has a large influence on the structural stress state by construction procedures, so that the bias multi-arch tunnel needs to be subjected to numerical analysis to determine a reasonable structural form.
At present, when a structure of a bias multi-arch tunnel is designed, commonly used bias multi-arch tunnel function functions mainly comprise polynomial fitting, a neural network model, a rational equation model, a Kriging model and other construction methods, but the methods often have the limitations of difficult solution, difficult convergence of oscillation often appearing in results, complex parameter estimation process and the like.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a bias multi-arch tunnel reliability evaluation method, so that the functional requirements of reserved deformation values of a plurality of measuring points around a hole can be considered simultaneously, and the purposes of high efficiency and accuracy can be achieved.
The purpose of the invention can be realized by the following technical scheme: a method for evaluating reliability of a bias multi-arch tunnel comprises the following steps:
s1, generating a designated number of parameter data sets by adopting a random uniform sampling method, and determining a numerical test scheme;
s2, according to the numerical test scheme determined in the step S1, carrying out numerical simulation calculation by using ANSYS finite element software to obtain the displacement of the designated measuring point, and combining the parameter data set to obtain an integral parameter-displacement data set;
s3, constructing a fitting model of parameters and displacement based on a Gradient Boosting Decision Tree (GBDT) algorithm, and selecting an optimal hyper-parameter combination by adopting a Bayesian algorithm to obtain an optimal fitting model;
s4, according to the reserved deformation value around the bias multi-arch tunnel, combining with an optimal fitting model, and inverting the surrounding rock parameters to be solved by adopting an NSGA-II algorithm to obtain optimized surrounding rock mechanical parameters;
and S5, calculating to obtain the corresponding reliable index of the primary support structure of the bias multi-arch tunnel according to the optimized surrounding rock mechanical parameters.
Further, the step S1 specifically includes the following steps:
s11, determining parameters to be selected and the range thereof through the field measured data;
and S12, generating a designated number of parameter data sets by adopting a random uniform sampling method, and determining a numerical test scheme.
Further, the step S2 specifically includes the following steps:
s21, acquiring an ANSYS calculation file;
s22, calling an ANSYS calculation file, recording the displacement change of each measuring point around the hole, and merging the displacement change with the parameter data set generated in the step S1;
s23, judging whether the current times of calling the ANSYS calculation file reaches a preset threshold value, if so, executing a step S24, otherwise, returning to execute the step S22;
and S24, outputting to obtain a combined integral parameter-displacement data set.
Further, the step S3 specifically includes the following steps:
s31, dividing the whole parameter-displacement data set into a training set and a test set according to a set proportion;
s32, constructing a fitting model of parameters and displacement based on the GBDT algorithm;
and S33, carrying out hyper-parameter tuning on the fitting model constructed in the step S32 by adopting a Bayesian algorithm and combining a training set and a testing set to obtain an optimal fitting model.
Further, the hyper-parameters in step S33 include learning _ rate, subsample, alpha, max _ depth, min _ samples _ split, min _ samples _ leaf, min _ weight _ fraction _ leaf, and max _ leaf _ nodes.
Further, the step S4 specifically includes the following steps:
s41, determining a loss function between a calculated value and a reserved deformation value of a fitting model of each measuring point of the multi-arch tunnel by combining an optimal fitting model according to the reserved deformation value of the periphery of the bias multi-arch tunnel;
s42, respectively setting corresponding objective functions at each measuring point, and determining the multi-objective functions;
and S43, carrying out iterative solution on the multi-target function by adopting an NSGA-II algorithm to obtain a minimum loss function, wherein parameters corresponding to the minimum loss function are the mechanical parameters of the surrounding rock corresponding to the reserved deformation value around the hole.
Further, the objective function corresponding to each measurement point in step S42 is a mean square error indicator.
Further, the multi-objective function in step S42 is specifically:
Figure BDA0003445002470000031
wherein liMean square error of the ith station, yi' and yiAnd respectively obtaining the calculated value of the ith measuring point and the reserved deformation value of the hole periphery of the measuring point through calculation of the optimal fitting model.
Further, the minimum loss function in step S43 is:
minL(p)＝{l1(p),l2(p),…,lh(p)}
Figure BDA0003445002470000032
wherein minL (p) is the minimum loss function value, p is the mechanical parameters of the surrounding rock, E, ν, v,c、
Figure BDA0003445002470000037
The elastic modulus, Poisson's ratio, cohesive force and friction angle of the surrounding rock are respectively.
Further, the corresponding reliable indexes of the primary support structure of the biased continuous arch tunnel in the step S5 are specifically:
Figure BDA0003445002470000033
wherein, muEAnd σEMean and standard deviation of the elastic modulus of the surrounding rock, muνAnd σνRespectively mean value and standard deviation of Poisson's ratio of surrounding rock, mucAnd σcRespectively is the mean value and the standard deviation of the cohesive force of the surrounding rock,
Figure BDA0003445002470000034
and
Figure BDA0003445002470000035
mean and standard deviation of internal friction angle of surrounding rock, E*、ν*、c*、
Figure BDA0003445002470000036
And respectively calculating the elastic modulus, Poisson' S ratio, binding force and internal friction angle of the surrounding rock corresponding to the reserved deformation value of the primary support structure of the bias multi-arch tunnel obtained in the step S43.
Compared with the prior art, the tunnel periphery reserved deformation value evaluation method based on single-target optimization can simultaneously consider the functional requirements of the hole periphery reserved deformation values of a plurality of measuring points, effectively improve the calculation precision and achieve the aim of accurately obtaining the reliability index.
According to the method, the GBDT algorithm is adopted to construct a parameter-displacement fitting model, and the super-parameters of the fitting model are adjusted and optimized by combining the Bayesian algorithm to obtain the optimal fitting model, so that the optimal fitting model can be quickly and reliably obtained on one hand, and the accuracy of subsequent calculation and optimization of the mechanical parameters of the surrounding rock is also ensured on the other hand.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a diagram illustrating the reliability index results in the example.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
Examples
The technical scheme is subsidized by a science and technology project of the Zhejiang province traffic hall (2020035) and a science and technology project of the twenty Central iron offices (qzsyscd-202010-. The technical solution is described in detail below with reference to fig. 1 and specific examples. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
As shown in fig. 1, a method for evaluating reliability of a bias multi-arch tunnel includes the following steps:
step 1: generating a parameter data set with a specified quantity by adopting a random uniform sampling method, and determining a numerical test scheme;
step 2: according to the test scheme determined in the step 1, carrying out numerical simulation calculation by adopting ANSYS finite element software to obtain the displacement of the specified measuring point;
and step 3: establishing a fitting model of parameters and displacement by a Gradient Boosting Decision Tree (GBDT) algorithm, and selecting an optimal hyper-parameter combination by adopting a Bayesian algorithm to obtain an optimal fitting model;
and 4, step 4: according to the reserved deformation value around the bias multi-arch tunnel, performing inversion on the surrounding rock parameters to be solved by adopting an NSGA-II algorithm on the basis of an optimal fitting model to obtain optimal surrounding rock mechanical parameters;
and 5: and (4) calculating the corresponding reliable indexes of the primary support structure of the bias multi-arch tunnel according to the calculation result of the step (4).
Wherein, the step 1 specifically comprises the following steps:
step 1-1: determining parameters to be selected and the range thereof through field measured data;
step 1-2: and generating a parameter data set with a specified quantity by adopting a random uniform sampling method, and determining a numerical test scheme.
The step 2 specifically comprises the following steps:
step 2-1: acquiring an ANSYS calculation file;
step 2-2: calling the calculation file in the step 2-1, recording the displacement change of the measuring point, and merging the displacement change with the parameter data set in the step 1;
step 2-3: judging whether the current calling times reach a preset threshold value, if so, executing the step 2-4, otherwise, returning to the step 2-2;
step 2-4: an overall parameter data set is obtained.
The step 3 specifically comprises the following steps:
step 3-1: according to the embodiment, 75-80% of the total number of the parameters and the displacement data is used as a training set, and 20-25% of the total number of the parameters and the displacement data is used as a test set, so that the data set is divided;
step 3-2: the method comprises the steps of establishing a fitting model of parameters and displacement through a GBDT algorithm, wherein the GBDT gradient lifting iterative decision tree is an integrated model, an addition model is adopted, and residual errors generated in a training process are continuously reduced to achieve an algorithm for classifying or regressing data, so that the strong performance of the algorithm is shown in various fields;
step 3-3: and (3) optimizing the learning _ rate, subsample, alpha, max _ depth, min _ samples _ split, min _ samples _ leaf, min _ weight _ fraction _ leaf and max _ leaf _ nodes hyper-parameters in the fitting model in the step 3-2 by adopting a Bayesian algorithm, so as to obtain an optimal fitting model.
The step 4 specifically comprises the following steps:
step 4-1: according to the reserved deformation value around the bias multi-arch tunnel, calculating a loss function between a calculated value of a fitting model of each measuring point of the multi-arch tunnel and the reserved deformation value on the basis of the optimal fitting model in the step 3-3;
step 4-2: and respectively setting an objective function for each measuring point, wherein each objective function is a Mean Square Error (MSE) index, and selecting the following objective functions:
Figure BDA0003445002470000051
in the formula IiMean Square Error (MSE) representing measured points, MSE ═ square of (true value-predicted value)/number of test sets, y'iAnd yiRespectively representing a measuring point calculation value obtained by calculating the optimal fitting model obtained in the step 3-3 and a hole periphery reserved deformation value of the measuring point;
step 4-3: calculating the minimum value of a loss function between a calculated value of a fitting model of each measuring point of the multi-arch tunnel and a reserved deformation value by adopting an NSGA-II algorithm: minL (p) ((l))1(p),l2(p),…,lh(p) and the corresponding parameter value is the surrounding rock mechanical parameter corresponding to the reserved deformation value around the hole, wherein,
Figure BDA0003445002470000052
E,ν,c,
Figure BDA0003445002470000053
the elastic modulus, Poisson's ratio, cohesive force and friction angle of the surrounding rock are respectively.
Step 5, calculating a reliable index beta of the primary support structure of the bias multi-arch tunnel according to surrounding rock mechanical parameters corresponding to the reserved deformation values of the primary support structure of the bias multi-arch tunnel obtained in the step 4-3 and through the following formula:
Figure BDA0003445002470000061
in the formula, muEAnd σERespectively representing the mean value and the standard deviation of the elastic modulus of the surrounding rock; mu.sνAnd σνRespectively representing the mean value and the standard deviation of the Poisson ratio of the surrounding rock; mu.scAnd σcRespectively representing the mean value and the standard deviation of the cohesive force of the surrounding rock;
Figure BDA0003445002470000062
and
Figure BDA0003445002470000063
respectively representing the mean value and the standard deviation of the internal friction angle of the surrounding rock; e*、ν*、c*、
Figure BDA0003445002470000064
And 4, respectively calculating values of the elastic modulus, Poisson's ratio, binding force and internal friction angle of the surrounding rock corresponding to the reserved deformation value of the primary support structure of the bias multi-arch tunnel obtained in the step 4-3.
In the embodiment, a certain road bias multi-arch tunnel is selected as an evaluation object, the height of the tunnel is 11.0m, the span is 12.16m, the buried depth of the tunnel is 30.6m, the reserved deformation of a primary support structure of the tunnel is 15cm, and the variation range of surrounding rock parameters is shown in table 1. The parameters of the surrounding rock where the tunnel is located have a large variation range, and in order to ensure the safety and reliability of construction, the reliability evaluation is carried out on the reserved deformation of the primary supporting structure of the tunnel according to the monitoring data.
TABLE 1 surrounding rock parameter variation Range
Figure BDA0003445002470000065
According to the value range shown in the table 1, 1000 groups of surrounding rock parameter data are generated in a random sampling mode, an ANSYS model of the tunnel is established, and displacement values of the measuring points are calculated. And inputting the established data set into a GBDT algorithm for learning to obtain an optimal fitting model of the surrounding rock parameters and the displacement. Because the displacement of the measured data in the x direction and the displacement of the measured data in the y direction have larger difference in value, two objective functions are set aiming at the displacement in different directions:
Figure BDA0003445002470000066
Figure BDA0003445002470000067
in the formula (I), the compound is shown in the specification,
Figure BDA0003445002470000068
respectively representing the displacement of the proxy model in the x direction and the y direction of a predicted measuring point i,
Figure BDA0003445002470000069
the displacement of the actual measurement point i in the x and y directions, Lx、LyIn this embodiment, the number of objective functions to be calculated by NSGA-II is two, and the reliability index β of the primary support structure of the bias multi-arch tunnel is calculated by the following formula:
Figure BDA00034450024700000610
the reliability index of each measurement point of the bias arch tunnel is shown in FIG. 2 (the figure in parentheses of each measurement point is the reliability index).

Claims (10)

1. A method for evaluating reliability of a bias multi-arch tunnel is characterized by comprising the following steps:
s1, generating a designated number of parameter data sets by adopting a random uniform sampling method, and determining a numerical test scheme;
s2, according to the numerical test scheme determined in the step S1, carrying out numerical simulation calculation by adopting ANSYS finite element software to obtain the displacement of the specified measuring point, and combining the parameter data set to obtain an integral parameter-displacement data set;
s3, constructing a fitting model of parameters and displacement based on a GBDT algorithm, and selecting an optimal hyper-parameter combination by adopting a Bayesian algorithm to obtain an optimal fitting model;
s4, according to the reserved deformation value around the bias multi-arch tunnel, combining with an optimal fitting model, and inverting the surrounding rock parameters to be solved by adopting an NSGA-II algorithm to obtain optimized surrounding rock mechanical parameters;
and S5, calculating to obtain the corresponding reliable index of the primary support structure of the bias multi-arch tunnel according to the optimized surrounding rock mechanical parameters.
2. The method for evaluating the reliability of the biased multi-arch tunnel according to claim 1, wherein the step S1 specifically comprises the following steps:
s11, determining parameters to be selected and the range thereof through the field measured data;
and S12, generating a designated number of parameter data sets by adopting a random uniform sampling method, and determining a numerical test scheme.
3. The method for evaluating the reliability of the bias multi-arch tunnel according to claim 1, wherein the step S2 specifically comprises the following steps:
s21, acquiring an ANSYS calculation file;
s22, calling an ANSYS calculation file, recording the displacement change of each measuring point around the hole, and merging the displacement change with the parameter data set generated in the step S1;
s23, judging whether the current times of calling the ANSYS calculation file reaches a preset threshold value, if so, executing a step S24, otherwise, returning to execute the step S22;
and S24, outputting to obtain a combined integral parameter-displacement data set.
4. The method for evaluating the reliability of the biased multi-arch tunnel according to claim 3, wherein the step S3 specifically comprises the following steps:
s31, dividing the whole parameter-displacement data set into a training set and a test set according to a set proportion;
s32, constructing a fitting model of parameters and displacement based on the GBDT algorithm;
and S33, carrying out hyper-parameter tuning on the fitting model constructed in the step S32 by adopting a Bayesian algorithm and combining a training set and a testing set to obtain an optimal fitting model.
5. The method as claimed in claim 4, wherein the hyper-parameters in step S33 include learning _ rate, subsample, alpha, max _ depth, min _ samples _ split, min _ samples _ leaf, min _ weight _ fraction _ leaf, and max _ leaf _ nodes.
6. The method for evaluating the reliability of the biased multi-arch tunnel according to claim 1, wherein the step S4 specifically comprises the following steps:
s41, determining a loss function between a calculated value of a fitting model of each measuring point of the multi-arch tunnel and a reserved deformation value according to the reserved deformation value of the periphery of the bias multi-arch tunnel and by combining an optimal fitting model;
s42, respectively setting corresponding objective functions at each measuring point, and determining the multi-objective functions;
and S43, carrying out iterative solution on the multi-target function by adopting an NSGA-II algorithm to obtain a minimum loss function, wherein the parameter corresponding to the minimum loss function is the surrounding rock mechanical parameter corresponding to the hole surrounding reserved deformation value.
7. The method for evaluating the reliability of the biased multi-arch tunnel according to claim 6, wherein the objective function corresponding to each measuring point in the step S42 is a mean square error indicator.
8. The method for evaluating the reliability of the biased multi-arch tunnel according to claim 7, wherein the multi-objective function in the step S42 is specifically as follows:
Figure FDA0003445002460000021
wherein liIs mean square error of the ith measurement point, y'iAnd yiAnd respectively obtaining the calculated value of the ith measuring point and the reserved deformation value of the hole periphery of the measuring point through calculation of the optimal fitting model.
9. The method for evaluating the reliability of a biased multi-arch tunnel according to claim 8, wherein the minimum loss function in the step S43 is as follows:
minL(p)＝{l1(p),l2(p),…,lh(p)}
Figure FDA0003445002460000022
wherein minL (p) is the minimum loss function value, p is the mechanical parameters of the surrounding rock, E, v, c,
Figure FDA0003445002460000023
The elastic modulus, Poisson's ratio, cohesive force and friction angle of the surrounding rock are respectively.
10. The method for evaluating the reliability of the bias multi-arch tunnel according to claim 9, wherein the reliability indexes corresponding to the primary support structure of the bias multi-arch tunnel in the step S5 are specifically:
Figure FDA0003445002460000031
wherein, muEAnd σEMean and standard deviation of the elastic modulus of the surrounding rock, muνAnd σνRespectively mean value and standard deviation of Poisson's ratio of surrounding rock, mucAnd σcRespectively is the mean value and the standard deviation of the cohesive force of the surrounding rock,
Figure FDA0003445002460000032
and
Figure FDA0003445002460000033
mean and standard deviation of internal friction angle of surrounding rock, E*、ν*、c*、
Figure FDA0003445002460000034
And respectively calculating the elastic modulus, Poisson' S ratio, binding force and internal friction angle of the surrounding rock corresponding to the reserved deformation value of the primary support structure of the bias multi-arch tunnel obtained in the step S43.
CN202111645505.XA 2021-12-30 2021-12-30 Bias multi-arch tunnel reliability evaluation method Pending CN114491735A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111645505.XA CN114491735A (en) 2021-12-30 2021-12-30 Bias multi-arch tunnel reliability evaluation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111645505.XA CN114491735A (en) 2021-12-30 2021-12-30 Bias multi-arch tunnel reliability evaluation method

Publications (1)

Publication Number Publication Date
CN114491735A true CN114491735A (en) 2022-05-13

Family

ID=81507746

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111645505.XA Pending CN114491735A (en) 2021-12-30 2021-12-30 Bias multi-arch tunnel reliability evaluation method

Country Status (1)

Country Link
CN (1) CN114491735A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115357994A (en) * 2022-10-20 2022-11-18 中国地质大学（北京） Soft rock tunnel surrounding rock parameter space random field modeling method, device and equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115357994A (en) * 2022-10-20 2022-11-18 中国地质大学（北京） Soft rock tunnel surrounding rock parameter space random field modeling method, device and equipment
CN115357994B (en) * 2022-10-20 2023-03-17 中国地质大学（北京） Soft rock tunnel surrounding rock parameter space random field modeling method, device and equipment

Similar Documents

Publication Publication Date Title
CN107301282B (en) Concrete dam mechanical parameter inversion method based on multi-source monitoring time sequence data
CN107391818A (en) A kind of Vibrating modal parameters recognition methods based on state observer
CN110289613B (en) Sensitivity matrix-based power distribution network topology identification and line parameter identification method
CN107607105B (en) Optical fibre gyro nonlinear temperature error compensating method based on fractional order differential
CN102779238A (en) Brushless DC (Direct Current) motor system identification method on basis of adaptive Kalman filter
CN110346005B (en) Coriolis mass flowmeter digital signal processing method based on deep learning
CN114491735A (en) Bias multi-arch tunnel reliability evaluation method
CN106443543A (en) Linearity testing method for current sensor
CN107634516A (en) A kind of distribution method for estimating state based on Grey Markov Chain
CN111090942B (en) High-sensitivity piezoresistive uniaxial force sensor design method based on topology optimization
CN114996983A (en) Soft rock tunnel reliability evaluation method
CN112163669A (en) Pavement subsidence prediction method based on BP neural network
CN110110406B (en) Slope stability prediction method for achieving LS-SVM model based on Excel computing platform
CN117251926B (en) Earthquake motion intensity index optimization method for earthquake response prediction
CN110245370A (en) A kind of high CFRD multiple target mechanics parameter inversion method
Sun et al. Mechanical state assessment of in-service cable-stayed bridge using a two-phase model updating technology and periodic field measurements
CN109884465B (en) Unidirectional ground fault positioning method based on signal injection method
CN111622274A (en) Method and system for predicting settlement of foundation of high-fill foundation of large grained soil in mountainous area
CN112733402B (en) Topological optimization design method of high-sensitivity low-crosstalk piezoresistive uniaxial force sensor
CN205826708U (en) Current source
CN113361146B (en) Improved particle swarm optimization-based manganese-copper shunt structure parameter optimization method
CN113489072B (en) Power distribution network state estimation method considering branch power pseudo measurement
CN109635452A (en) A kind of efficient multimodal stochastic uncertainty analysis method
CN113820062A (en) Temperature compensation method of six-dimensional force sensor
CN111159935A (en) BP neural network parameter calibration method based on LHS

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination