CN115828374A - Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period - Google Patents
Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period Download PDFInfo
- Publication number
- CN115828374A CN115828374A CN202211422110.8A CN202211422110A CN115828374A CN 115828374 A CN115828374 A CN 115828374A CN 202211422110 A CN202211422110 A CN 202211422110A CN 115828374 A CN115828374 A CN 115828374A
- Authority
- CN
- China
- Prior art keywords
- deformation
- tunnel
- lssvm
- data
- coefficient
- 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
Links
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a method and a system for predicting non-uniform deformation in a composite stratum tunnel construction period, which are suitable for improving a traditional tunnel surrounding rock deformation displacement monitoring method, extracting geological sketch data and full-section scanning map data, classifying and quantifying tunnel deformation monitoring data, defining an average deformation coefficient, an uneven deformation coefficient, a sectional deformation coefficient and an abnormal deformation coefficient to measure the non-uniform deformation degree of a tunnel, and establishing a non-uniform deformation grading method in the composite stratum tunnel construction period; based on a PSO-LSSVM combined algorithm and a numerical simulation means, a stratum boundary inclination angle, a stratum proportion, a ground stress and a pore water pressure are used as input, each index grade is used as output, the association degree and the deformation grade discrimination standard of each grading coefficient and the tunnel non-uniform deformation grade are calculated, and a composite stratum tunnel surrounding rock non-uniform deformation prediction model is established; and inputting the data acquired on site into a PSO-LSSVM composite stratum tunnel deformation intelligent prediction system to obtain a prediction result.
Description
Technical Field
The invention belongs to the field of rock-soil grading and deformation grade prediction, and relates to a method and a system for predicting non-uniform deformation in a composite stratum tunnel construction period.
Background
The surrounding rock properties of the composite stratum frequently change, the physical and mechanical properties of different surrounding rocks have obvious differences, the uneven stress release of the soft and hard surrounding rocks easily causes uneven large deformation in the excavation process, and the frequent stratum change also causes serious safety threats to TBM equipment and operators. The method has the advantages that the deformation of the tunnel in the composite stratum is monitored in real time, effectively graded and intelligently predicted, the support strength of the primary foundation is optimized for constructors, reference is provided for determining the local reinforced support range, and basis is provided for prevention and control of tunnel deformation damage.
According to the knowledge of the inventor, the traditional monitoring and measuring data only reflect vertical settlement and horizontal convergence but cannot reflect the nonlinear change of the axial and radial curved surfaces of the tunnel face, namely the non-uniform deformation of the tunnel of the composite stratum is difficult to monitor in real time; in the surrounding rock deformation grading method, the engineering geological stratum parameters and the non-uniform deformation of each subsection are rarely considered; the traditional tunnel deformation grade prediction mainly adopts methods such as empirical formulas and numerical simulation, but the large and uneven deformation of the tunnel in the composite stratum is influenced by various factors such as engineering geological factors and construction factors, so that the problem belongs to nonlinear solution.
Disclosure of Invention
In order to solve the problems, the invention provides a method and a system for predicting the non-uniform deformation of a composite stratum tunnel in the construction period. And the classification result is well matched with the actual monitoring grade by applying the actual tunnel engineering, and the real-time performance and the applicability are better.
According to some embodiments, the invention adopts the following technical scheme:
in a first aspect, the invention provides a heterogeneous deformation grading method suitable for a composite stratum tunnel construction period, which comprises the following steps:
acquiring deformation data of each existing tunnel by using a tunnel monitoring system, and obtaining each deformation coefficient according to the deformation data;
acquiring simulated geological deformation data by using the numerical simulation data;
step three, establishing an initial database by using the data obtained in the step one and the step two;
fourthly, constructing an LSSVM learning model under the composite stratum tunnel non-uniform deformation classification theory based on a particle swarm optimization-least square support vector machine PSO-LSSVM combined intelligent algorithm, and inputting learning sample data of an initial database into the LSSVM learning model;
optimizing parameters of the LSSVM learning model by using a PSO algorithm, and establishing a PSO-LSSVM prediction model as a real-time online grading model of the non-uniform deformation of the composite stratum tunnel by using the obtained optimized parameters; and inputting the training set of the samples to be tested into a PSO-LSSVM prediction model to obtain a real-time grading output result, and predicting the non-uniform deformation of the composite stratum tunnel in the construction period according to the output result.
As a further technical scheme, according to the difference between the geological sketch and the tunnel section scanning data after the initial excavation of the tunnel and the stable deformation of the tunnel in the full-section scanning diagram, the complete deformation data of the tunnel section of the composite stratum is obtained.
The method establishment method in the step is as follows: determining an average deformation coefficient according to the deformation data condition of the composite stratum tunnel
And the uneven deformation coefficient xi, the segmented deformation coefficient zeta and the abnormal deformation coefficient psi replace the traditional deformation evaluation index. Wherein the average deformation coefficient
The integral condition of non-uniform deformation is represented, the non-uniform deformation coefficient xi measures the condition of non-uniform section deformation, the subsection deformation coefficient zeta determines the abnormal intrusion deformation position of the tunnel, and the abnormal deformation coefficient psi measures the intrusion deformation size.
And in the third step, a part of deformation data of the initial database is obtained by the field monitoring data in the first step, and the other part of the deformation data is subjected to modeling calculation by the numerical simulation software in the second step, so that the influence of different levels of factors such as the inclination angle, the occupation ratio, the ground stress and the pore water pressure of the tunnel on the deformation is reflected.
In the fourth step, the LSSVM learning model converts inequality constraint conditions into equality constraint conditions, converts quadratic programming problems into linear equation problems, and meanwhile, optimization and prediction of LSSVM parameters are fused into a PSO algorithm, so that the algorithm precision is improved.
The PSO algorithm optimization method in the fifth step comprises the following steps: and finding the optimal punishment factor c and the optimal nuclear parameter g by using a particle swarm algorithm, then iterating until the particle swarm fitness is globally optimal, stopping, obtaining the optimal punishment factor c and the optimal nuclear parameter g, and then predicting each index.
And fifthly, establishing a prediction model as a composite stratum tunnel non-uniform deformation real-time classification model by using the obtained optimized parameter penalty factor c and the nuclear parameter g, inputting the composite stratum tunnel non-uniform deformation classification coefficient obtained in the first step into the LSSVM prediction model by using the accurate monitoring data of vault settlement and horizontal convergence, geological sketch data and a full-section scanning map data sample training set obtained in the first step and the second step in real time, and obtaining a real-time classification output result.
In a second aspect, the invention relates to a system for predicting the non-uniform deformation grade of a composite stratum tunnel in a construction period, which comprises:
the sample database construction module is configured to acquire deformation data of each existing tunnel by using a tunnel monitoring system and obtain each deformation coefficient according to the deformation data; acquiring simulated geological deformation data by using numerical simulation data; establishing an initial database based on the deformation coefficient and the simulated geological deformation data;
the prediction model building module is configured to build an LSSVM learning model under the composite stratum tunnel non-uniform deformation classification theory based on particle swarm optimization-least square support vector machine PSO-LSSVM combined intelligent algorithm, and the learning sample data of the initial database are input into the LSSVM learning model; optimizing parameters of an LSSVM learning model by using a PSO algorithm, and establishing a PSO-LSSVM prediction model as a composite stratum tunnel non-uniform deformation real-time online grading model by using the obtained optimized parameters;
the prediction module inputs a training set of samples to be tested into a PSO-LSSVM prediction model to obtain a real-time grading output result, and predicts the non-uniform deformation of the composite stratum tunnel in the construction period according to the output result;
in a fourth aspect, the present invention further provides a terminal device, including a processor and a computer-readable storage medium, where the processor is configured to implement the instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the steps of the method for predicting the nonuniform deformation of the composite stratum tunnel.
Compared with the prior art, the beneficial effect of this disclosure is: .
1. The method is based on the actual tunnel engineering, the geological information, the construction data and the monitoring measurement data of the actual engineering are widely collected, and the heterogeneous deformation data sample set of the composite stratum tunnel is enriched, so that the composite stratum tunnel heterogeneous deformation evaluation system with wide applicability is established. And inducing the change rule of the tunnel non-uniform deformation index under the influence of different stratum parameters, and establishing an initial sample library, wherein the established sample library has the advantages of universality and instantaneity. The optimized sample database is established, the particle swarm optimization PSO algorithm is scientific and reasonable, the accuracy of the prediction result of the least square support vector machine LSSVM learning model is greatly improved, the composite stratum tunnel non-uniform deformation prediction model is established, and the subsequent real-time monitoring data is combined, so that the method has unique superiority and high accuracy of the prediction result.
2. When the heterogeneous deformation of the tunnel in the composite stratum is predicted, the heterogeneous deformation grade of the tunnel can be obtained only by inputting the average deformation coefficient, the uneven deformation coefficient, the sectional deformation coefficient and the abnormal deformation coefficient which are obtained by calculating the geological condition, the construction condition and the deformation monitoring data of the tunnel to be predicted as input parameters into the obtained PSO-LSSVM model, and the method is simple and reliable. The method can accurately predict the deformation of the tunnel in the composite stratum, optimize the support strength of the primary foundation and provide reference for determining the local reinforced support range for constructors.
Advantages of additional aspects of the invention 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 the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic diagram of a method for predicting non-uniform deformation during a composite formation tunnel construction period according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a non-uniform deformation curve during the construction period of a composite formation tunnel according to an embodiment of the present invention;
Detailed Description
The invention is further explained by the following embodiments in conjunction with the drawings.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The invention provides a non-uniform deformation prediction method suitable for a composite stratum tunnel in a construction period on the basis of widely collecting surrounding rock geological parameters and deformation data acquired in real time of a built and under-built composite stratum tunnel and combining a particle swarm optimization algorithm and a least square support vector machine method. According to the method, actual engineering geological conditions, construction conditions and deformation data are combined, the non-uniform deformation rule and geological change characteristics of the composite stratum tunnel are comprehensively summarized and analyzed, an average deformation coefficient, an uneven deformation coefficient, a segmented deformation coefficient and an abnormal deformation coefficient are defined, the traditional deformation evaluation index is replaced, and a composite stratum tunnel non-uniform deformation initial sample database is established; the method comprises the steps of converting inequality constraint conditions into equality constraint conditions through an LSSVM learning model, converting a quadratic programming problem into a linear equation problem, fusing LSSVM parameter optimization and prediction into a PSO algorithm, improving algorithm precision, and optimizing an original sample database; and constructing a composite stratum tunnel non-uniform large-deformation PSO-LSSVM prediction model by taking the calculated grading coefficient index as an input parameter and the non-uniform deformation grade as an output parameter. The method is based on actual engineering of the actual engineering tunnel, historical data corresponding to deformation indexes are obtained, geological conditions, construction conditions and deformation data of all existing tunnels are obtained, geological change characteristics are obtained by utilizing field data and numerical simulation data, and the established sample database has universality and representativeness. The method has the advantages that the particle swarm optimization is used for finding the globally optimal punishment factor and kernel parameter, the accuracy is high after optimization, the particle swarm optimization is proved to obviously improve the accuracy of the least square support vector machine, and the accuracy of the prediction result of the LSSVM learning model is greatly improved. The method has the advantages of real sample data, rich and representative information quantity. The database optimization method is scientific and reasonable, the prediction method has unique superiority, and the accuracy of the prediction result is high. The method has the advantages that the deformation of the tunnel in the composite stratum is monitored in real time, effectively graded and intelligently predicted, the support strength of the primary foundation is optimized for constructors, reference is provided for determining the local reinforced support range, and basis is provided for prevention and control of tunnel deformation damage. The method has important guiding significance for the prediction and safe construction of the non-uniform deformation of the tunnel of the composite stratum.
The embodiment provides a method for predicting non-uniform deformation in a composite stratum tunnel construction period, as shown in fig. 1, the method specifically includes:
(1) Selecting the geological parameters and deformation data of the surrounding rock acquired in real time to obtain deformation coefficients, wherein the deformation coefficients comprise average deformation coefficients
And the uneven deformation coefficient xi, the segmented deformation coefficient zeta and the abnormal deformation coefficient psi replace the traditional deformation evaluation index. Wherein the average deformation coefficient
The integral condition of non-uniform deformation is represented, the non-uniform deformation coefficient xi measures the condition of non-uniform section deformation, the subsection deformation coefficient zeta determines the abnormal intrusion deformation position of the tunnel, and the abnormal deformation coefficient psi measures the intrusion deformation size.
Average deformation coefficient in the first step
Comprises the following steps:
in the formula, L is the circumferential length of the tunnel (excluding an inverted arch), δ (L) is a tunnel deformation function, and is characterized by the distance between the actual section of the tunnel at the corresponding position and the initial section, and R is the initial radius of the tunnel.
In the first step, the non-uniform deformation coefficient xi is as follows:
in the formula, S Invasion Is the penetration area of the cross section, S Expanding device Is the area of the outer expansion of the cross section, n 1 The number of penetration zones of the cross section,/ n1 Is the arc length of the penetration part of the section, delta 1 (l) As a function of deformation of the encroaching part of the section, n 2 Number of area of the cross-section n2 The arc length of the flaring part of the cross section is delta 2 (l) Is a deformation function of the flaring portion.
The segmented deformation coefficient zeta in the first step is as follows:
in the formula (I), the compound is shown in the specification,
average intrusion amount for the intrusion portion of the corresponding zone,
average amount of flare for the flare portion of the corresponding region, R n For the equivalent radius of the tunnel in the corresponding area, d is the deformation reserved for the tunnel, L n Is the corresponding zone arc length.
The abnormal deformation coefficient psi in the step one is as follows:
in the formula, S Invasion Denotes the area of the penetration portion, L Invasion Indicating that the encroachment portion corresponds to the arc length.
(2) Acquiring geological change characteristics based on the field data and the numerical simulation data, and establishing an initial database; the method for dividing the level of each factor of the initial database comprises the following steps: the formation occupation ratio is divided according to three different occupation ratios of 1, 2. The applied ground stress was classified into three levels of 0MPa,4MPa and 8 MPa. The underground water condition is realized by adjusting the pore water pressure, which is divided into three levels of 0MPa,0.5MPa and 1 MPa. Taking the intersection point of the stratum boundary and the central horizontal line of the tunnel height as an origin, taking the horizontal plane as 0 degrees, turning anticlockwise as positive, turning clockwise as negative, and dividing the inclination angle of the rock stratum interface according to five angles of 0 degrees, 45 degrees, 90 degrees, 135 degrees and 180 degrees.
(3) Constructing an LSSVM learning model under the composite stratum tunnel non-uniform deformation classification theory based on a particle swarm optimization-least square support vector machine PSO-LSSVM combined intelligent algorithm, and inputting obtained learning sample data into the LSSVM learning model;
the LSSVM learning model in the third step is as follows: the LSSVM converts inequality constraint conditions into equality constraint conditions, converts a quadratic programming problem into a linear equation problem, and when the LSSVM utilizes a structural risk principle, the optimization problem becomes:
wherein, the corresponding constraint conditions are as follows:
y i [(w T *x i )+b]＝1-ξ i ,i＝1,2,g,n
in the formula, xi i Representing the relaxation factor, γ is the regularization parameter, also called penalty factor, and n is the population size.
Establishing a Lagrange equation:
l minimizes ω, b, ξ, α, the partial derivative is 0:
the four conditions according to the above equation can be listed as a linear equation system to solve a, b:
where Ω is the kernel matrix, I is the identity matrix, and y, a are the vectors. Obtaining:
and finally, obtaining a classification decision model of the LSSVM, wherein the classification decision model comprises the following steps:
the learning sample data in the third step is a learning sample of the initial database, the samples of the database are formed into a sample set, and n particles X = (X) are considered 1 ,X 2 ,…,X n ) Wherein the position of the ith particle is X i ＝(x i1 ,x i2 ,…,x id ) T Is mixing X i Introducing a fitness function f (X) i ) And calculating the fitness value of the particle position. The velocity of the ith particle is V i ＝(v i1 ,v i2 ,…,v id ) T Wherein the individual extremum of the ith particle is P i ＝(P i1 ,P i2 ,…,P id ) T The global extreme is P g ＝(P g1 ,P g2 ,…,P gd ) T . In the optimization process, the velocity and position of the particles are tracked to individual optimal particles and clusters by using the following equationsVolume-optimal particle update.
In the third step: n is the number of samples, X = (X) 1 ,X 2 ,…,X n ) Four-dimensional vector representing deformation grading coefficient, including average deformation coefficient
Uneven distortion coefficient xi, piecewise distortion coefficient zeta and abnormal distortion coefficient psi, f (X) i ) Is the output vector and the value is the corresponding deformation level; learning the deformation level f (X) of a sample i ) The composite stratum tunnel heterogeneous deformation grading method is used for obtaining the composite stratum tunnel heterogeneous deformation grading method in the step one.
Fitness function f (X) in the third step i )：
Wherein k is the current iteration number, n is the population size, and X k The position of the kth particle.
The positions of the sample particles in the third step are as follows:
X k+1 id ＝X k id +V k id
wherein X k id And V k id Representing the position and velocity individual extrema for the ith particle in the (k + 1) th iteration.
Velocity of ith sample particle in the k +1 th iteration in the third step
Comprises the following steps:
wherein, omega is the inertia weight and controls how much speed the ith particle inherits,
is as followsThe velocity of the ith sample particle after k iterations,
and
representing the individual extremum and the global extremum of the ith particle,
and
is the individual and global position of the kth particle, c 1 ,c 2 The speed calculation is controlled for the acceleration factor. r is 1 ,r 2 The random numbers are two random numbers, the value range is (0-1), and the randomness of searching can be increased. To prevent blind searching of particles, the position and velocity are usually limited to [ -X [ ] max ，X max ]、[-V max ，V max ]。
(4) And optimizing parameters of the LSSVM learning model by using a PSO algorithm, establishing a prediction model by using the obtained optimized parameters as a real-time online classification model of the non-uniform deformation of the composite stratum tunnel, and inputting a sample training set consisting of real-time sample data into the LSSVM prediction model to obtain a real-time classification output result.
TABLE 1 standards for determination of respective deformation levels
Further, in the step (1), the required data includes historical data corresponding to each grading index, geological conditions, construction conditions and deformation data of each existing tunnel are obtained, an average deformation coefficient, an uneven deformation coefficient, a segmented deformation coefficient and an abnormal deformation coefficient are defined, and a prediction model deformation grade discrimination standard in table 1 is established.
Further, in the step (2), the geological change characteristics are obtained by using the field data, and an initial sample database of the composite stratum tunnel non-uniform deformation is established. The actual engineering section profile data is shown in table 2.
TABLE 2 actual engineering tunnel measured data set
Further, in the step (3), the engineering site monitoring data and the geological model data are substituted into an LSSVM learning model, and are configured to take the calculated average deformation coefficient, uneven deformation coefficient, segmental deformation coefficient and abnormal deformation coefficient as input parameters, and take each segmental deformation level as an output parameter, so as to establish an optimized sample database and construct a composite stratum tunnel nonuniform deformation prediction model.
Further, in the step (4), a sample data set composed of the real-time sample data to be detected is input into the LSSVM prediction model, so as to obtain a real-time hierarchical output result. As shown in table 3.
TABLE 3 actual engineering Tunnel prediction result data set
Furthermore, in the step (4), the accuracy of the prediction grades obtained from the table 3 in the training model is 93.33% (14/15) of average deformation grade, 86..67% (13/15) of abnormal deformation grade, 93.33% (14/15) of uneven deformation grade and 93.33% (14/15) of segmented deformation grade, and the grading accuracy of the training set meets the test requirement. 15 groups of test sample data are brought into the SVM prediction model, and compared with the classification result of the traditional surrounding rock classification result, the accuracy rate reaches 100%, and the test effect is good.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A prediction method for nonuniform deformation in a composite stratum tunnel construction period is characterized by comprising the following steps: the method comprises the following steps:
acquiring deformation data of each existing tunnel by using a tunnel monitoring system, and obtaining each deformation coefficient according to the deformation data;
acquiring simulated geological deformation data by using the numerical simulation data;
step three, establishing an initial database by using the data obtained in the step one and the step two;
fourthly, constructing an LSSVM learning model under the composite stratum tunnel non-uniform deformation classification theory based on a particle swarm optimization-least square support vector machine PSO-LSSVM combined intelligent algorithm, and inputting learning sample data of an initial database into the LSSVM learning model;
fifthly, optimizing parameters of the LSSVM learning model by using a PSO algorithm, and establishing a PSO-LSSVM prediction model as a composite stratum tunnel non-uniform deformation real-time online grading model by using the obtained optimized parameters; and inputting the training set of the samples to be tested into a PSO-LSSVM prediction model to obtain a real-time grading output result, and predicting the non-uniform deformation of the composite stratum tunnel in the construction period according to the output result.
2. The heterogeneous deformation grading method suitable for the composite stratum tunnel construction period as claimed in claim 1, wherein: the first step is as follows: the method for acquiring the deformation data comprises the following steps:
and according to the difference between the tunnel section scanning data of initial tunnel excavation and stable tunnel deformation in the geological sketch and the full-section scanning diagram, acquiring complete deformation data of the tunnel section of the composite stratum.
3. The heterogeneous deformation grading method suitable for the composite stratum tunnel construction period as claimed in claim 1, wherein: in step (b)In the first step: the deformation coefficient comprises an average deformation coefficient
An uneven distortion coefficient ξ, a segmented distortion coefficient ζ, and an abnormal distortion coefficient ψ.
4. The heterogeneous deformation grading method suitable for the composite stratum tunnel construction period as claimed in claim 1, wherein: in the fourth step, the LSSVM learning model is as follows: the LSSVM converts inequality constraint conditions into equality constraint conditions, converts a quadratic programming problem into a linear equation problem, and when the LSSVM utilizes a structural risk principle, the optimization problem becomes:
wherein, the corresponding constraint conditions are as follows:
y i [(w T *x i )+b]＝1-ξ i ,i＝1,2,...,n
in the formula, xi i Representing a relaxation factor, gamma is a regularization parameter, also called a penalty coefficient, and n is the population size;
establishing a Lagrange equation:
l minimizes ω, b, ξ, α, the partial derivative is 0:
the four conditions according to the above equation can be listed as a linear equation system to solve a, b:
where Ω is the kernel matrix, I is the identity matrix, and y, a are the vectors. Solving the following steps:
and finally, obtaining a classification decision model of the LSSVM, wherein the classification decision model comprises the following steps:
5. the heterogeneous deformation grading method suitable for the composite stratum tunnel construction period as claimed in claim 1, wherein: the PSO-LSSVM prediction model in the step five is as follows:
the PSO algorithm optimizes the LSSVM learning model, wherein: x = (X) 1 ,X 2 ,…,X n ) Four-dimensional vector representing deformation grading coefficient, including average deformation coefficient
Uneven distortion coefficient xi, piecewise distortion coefficient zeta and abnormal distortion coefficient psi, f (X) i ) Is the output vector and the value is the corresponding deformation level;
fitness function f (X) i )：
Wherein k is the current iteration number, n is the population size, and X k The position of the kth particle.
The positions of the sample particles are:
X k+1 id ＝X k id +V k id
wherein X k id And V k id Representing the position and velocity individual extrema of the ith particle in the (k + 1) th iteration.
In the optimization process, the velocity and position of the particle are updated by tracking the velocity of the ith sample particle in the (k + 1) th iteration using the following equation for the single optimal particle and the population optimal particle
Comprises the following steps:
wherein, omega is the inertia weight and controls how much speed the ith particle inherits,
for the velocity of the ith sample particle after the kth iteration,
and
representing the individual extremum and the global extremum of the ith particle,
and
is the individual and global position of the kth particle, c 1 ,c 2 The speed calculation is controlled for the acceleration factor. r is 1 ,r 2 The random numbers are two random numbers, the value range is (0-1), and the randomness of searching can be increased.
6. The heterogeneous deformation grading method suitable for the composite stratum tunnel construction period as claimed in claim 1, wherein: in the fourth step, the LSSVM learning model converts inequality constraint conditions into equality constraint conditions, converts the quadratic programming problem into a linear equation problem, and meanwhile, optimization and prediction of LSSVM parameters are fused into a PSO algorithm, so that the algorithm precision is improved.
7. The heterogeneous deformation grading method suitable for the composite stratum tunnel construction period as claimed in claim 1, wherein: and fifthly, finding the optimal punishment factor c and the optimal kernel parameter g by using a particle swarm algorithm, then iterating until the particle swarm fitness is globally optimal, stopping, obtaining the optimal punishment factor c and the optimal kernel parameter g, predicting each index, and establishing a PSO-LSSVM prediction model by using the obtained optimal parameter punishment factor c and the kernel parameter g.
8. A non-uniform deformation grade prediction system suitable for a composite stratum tunnel construction period is characterized in that: the method comprises the following steps:
the sample database construction module is configured to acquire deformation data of each existing tunnel by using a tunnel monitoring system and obtain each deformation coefficient according to the deformation data; acquiring simulated geological deformation data by using the numerical simulation data; establishing an initial database based on the deformation coefficient and the simulated geological deformation data;
the prediction model building module is configured to build an LSSVM learning model under the composite stratum tunnel non-uniform deformation classification theory based on a particle swarm optimization-least squares support vector machine (PSO-LSSVM) combined intelligent algorithm, and the learning sample data of the initial database is input into the LSSVM learning model; optimizing parameters of an LSSVM learning model by using a PSO algorithm, and establishing a PSO-LSSVM prediction model as a composite stratum tunnel non-uniform deformation real-time online grading model by using the obtained optimized parameters;
and the prediction module is used for inputting the training set of the samples to be tested into the PSO-LSSVM prediction model to obtain a real-time grading output result and predicting the non-uniform deformation of the composite stratum tunnel in the construction period according to the output result.
9. A computer-readable storage medium characterized by: computer program stored thereon, characterized in that the instructions are loaded by a processor of a terminal device and execute a method for predicting non-uniform deformation levels of composite formation tunnels according to any one of claims 1 to 8.
10. A terminal device is characterized in that: comprising a processor and a computer readable storage medium, the processor for implementing instructions; the computer readable storage medium is used for storing a plurality of instructions, the instructions are suitable for being loaded by a processor and executing the steps of any one of the claims 1-8, wherein the steps are suitable for the prediction method of the nonuniform deformation of the composite stratum tunnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211422110.8A CN115828374A (en) | 2022-11-14 | 2022-11-14 | Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211422110.8A CN115828374A (en) | 2022-11-14 | 2022-11-14 | Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115828374A true CN115828374A (en) | 2023-03-21 |
Family
ID=85528036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211422110.8A Pending CN115828374A (en) | 2022-11-14 | 2022-11-14 | Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115828374A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116740900A (en) * | 2023-08-15 | 2023-09-12 | 中铁七局集团电务工程有限公司武汉分公司 | SVM-based power construction early warning method and system |
| CN116975623A (en) * | 2023-05-04 | 2023-10-31 | 西南交通大学 | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method |
| CN117494483A (en) * | 2024-01-02 | 2024-02-02 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
-
2022
- 2022-11-14 CN CN202211422110.8A patent/CN115828374A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975623A (en) * | 2023-05-04 | 2023-10-31 | 西南交通大学 | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method |
| CN116975623B (en) * | 2023-05-04 | 2024-01-30 | 西南交通大学 | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method |
| CN116740900A (en) * | 2023-08-15 | 2023-09-12 | 中铁七局集团电务工程有限公司武汉分公司 | SVM-based power construction early warning method and system |
| CN116740900B (en) * | 2023-08-15 | 2023-10-13 | 中铁七局集团电务工程有限公司武汉分公司 | SVM-based power construction early warning method and system |
| CN117494483A (en) * | 2024-01-02 | 2024-02-02 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
| CN117494483B (en) * | 2024-01-02 | 2024-03-19 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115828374A (en) | Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period | |
| Xue et al. | A two-step comprehensive evaluation model for rockburst prediction based on multiple empirical criteria | |
| CN112364422B (en) | MIC-LSTM-based dynamic prediction method for shield construction earth surface deformation | |
| CN109165406A (en) | The quick dynamic classification prediction technique of country rock during a kind of constructing tunnel | |
| CN115423167A (en) | Subway deep foundation pit construction safety early warning and decision-making assisting method and system | |
| CN112100727A (en) | Early warning prevention and control method for water inrush of water-rich tunnel under influence of fault fracture zone | |
| CN103205972A (en) | Method for analyzing relationship between deformation of foundation pit and ground subsidence outside of foundation pit | |
| CN112989262A (en) | Method for predicting maximum horizontal displacement of adjacent tunnel by considering excavation process of foundation pit | |
| CN117994462B (en) | Digital mine topography model building method | |
| Hassan et al. | Predictive models to evaluate the interaction effect of soil-tunnel interaction parameters on surface and subsurface settlement | |
| CN113128106B (en) | Method for determining surface subsidence caused by shield construction of karst stratum | |
| Li et al. | Development of a seismic vulnerability and risk model for typical bridges considering innovative intensity measures | |
| CN113221399B (en) | Decision method for dividing scheme of railway tunnel fabricated lining components | |
| CN113111411B (en) | System and method for reinforcing deep silt foundation | |
| CN111946397B (en) | Rapid method for on-site evaluation of integrity of tunnel face rock and soil mass of heading machine | |
| CN117113842A (en) | Tunnel surrounding rock deformation prediction method based on PSO-LSTM model | |
| Pan et al. | Assessment method of slope excavation quality based on point cloud data | |
| CN113268808B (en) | Digital detection method for top-lifting construction of extremely-soft and weak broken surrounding rock door type system | |
| CN114066271A (en) | Tunnel water inrush disaster monitoring and management system | |
| CN115169243A (en) | GA-PSO-GLSSVM algorithm-based soil-rock composite stratum deep foundation pit deformation time sequence prediction method | |
| Jelušič et al. | An adaptive network fuzzy inference system approach for site investigation | |
| Lee et al. | Machine learning-based predictive model of ground subsidence risk using characteristics of underground pipelines in urban areas | |
| CN111663935A (en) | Method and system for evaluating shaft annulus air tightness | |
| Jiaxu et al. | A water leakage risk assessment model for shield tunnel based on Kalman filter data fusion method | |
| CN118095813B (en) | Visual monitoring method and system for foundation settlement based on BIM technology |
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 |