CN114692441B - Loess landslide stability prediction method, electronic equipment and storage medium - Google Patents
Loess landslide stability prediction method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114692441B CN114692441B CN202210146901.6A CN202210146901A CN114692441B CN 114692441 B CN114692441 B CN 114692441B CN 202210146901 A CN202210146901 A CN 202210146901A CN 114692441 B CN114692441 B CN 114692441B
- Authority
- CN
- China
- Prior art keywords
- sliding surface
- landslide
- error function
- loess
- shear strength
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/60—3D [Three Dimensional] animation of natural phenomena, e.g. rain, snow, water or plants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- 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
- G06F2111/10—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
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/23—Dune restoration or creation; Cliff stabilisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Probability & Statistics with Applications (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Remote Sensing (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a loess landslide stability prediction method, electronic equipment and a storage medium, and belongs to the field of stability prediction. The method comprises the following steps: acquiring shear strength parameters of a target area, and constructing a shear strength parameter mean error function; constructing a sliding surface position error function according to sliding surface observation information of first destabilization of a target sliding surface and a critical sliding surface determined by finite difference numerical simulation calculation; calculating a landslide stability coefficient through finite difference strength folding and subtracting, and constructing a landslide stability coefficient error function; combining the three constructed error functions, and carrying out multiple iterations by using a genetic algorithm based on multiple groups of random sampling samples to obtain an optimal parameter group; and constructing a simulated sliding surface according to other parameters of the target landslide and the optimal parameter set, and predicting a stability prediction result of the target landslide under the condition that the consistency characterization is correct. The present application aims to obtain a more reliable inverse analysis result and to predict the stability of landslide more accurately.
Description
Technical Field
The embodiment of the application relates to the technical field of stability prediction, in particular to a loess landslide stability prediction method, electronic equipment and a storage medium.
Background
Along with the high-speed development of economy, human activities such as engineering construction, agricultural irrigation and resource development are more frequent, but the problem of frequent landslide geological disasters is also accompanied in the development process, and the landslide geological disasters have the characteristics of large quantity, wide distribution and large loss, so that the risk assessment, prevention and control of landslide are particularly important for protecting the safety of lives and properties of people.
The acquisition of accurate and reliable physical mechanical calculation parameters is a basic precondition for developing landslide stability evaluation, a large number of parameters for researching landslide stability, such as the residual strength parameters of landslide soil and the shear strength of saturated remolded loess under different confining pressures and shear rates, are obtained through a large number of experimental researches, and the experimental results provide important data support for the research of loess landslide stability, but the uncertain factors of indoor experimental researches are more, and the physical mechanical parameters of undisturbed loess are difficult to obtain. Meanwhile, due to the scale effect problem, the experimental research results are difficult to characterize the parameter characteristics of the real landslide hazard.
The method comprises the steps of carrying out parameter inverse analysis according to landslide hazard observation information, providing an important way for obtaining reliable loess landslide calculation parameters, for example, obtaining unsaturated loess landslide cohesive force and internal friction angle by utilizing landslide front slope body geometry and physical parameter inversion, deducing a parameter inversion display expression based on limit balance theory through judgment of a critical arc sliding surface, and carrying out slope stability parameter inversion analysis; and a landslide shear strength parameter reliability inverse analysis method is researched based on a three-dimensional upper limit analysis theory.
Although these research results improve the accuracy of the landslide stability calculation parameters to a certain extent, most of them only consider the stability coefficient or deformation characteristic as constraint conditions, so that the reliability of the result of the inverse analysis is not ideal, and therefore, how to improve the result of the inverse analysis and predict the landslide stability by using the result of the inverse analysis is a problem to be solved urgently.
Disclosure of Invention
The embodiment of the application provides a loess landslide stability prediction method, electronic equipment and a storage medium, and aims to obtain a more reliable anti-analysis result and more accurately predict landslide stability.
In a first aspect, an embodiment of the present application provides a loess landslide stability prediction method, including:
acquiring shear strength parameters of a target area, wherein the shear strength parameters comprise data of effective cohesive force of a plurality of groups of natural loess, effective internal friction angles of a plurality of groups of natural loess, effective cohesive force of a plurality of groups of saturated loess and effective internal friction angles of a plurality of groups of saturated loess, and constructing a mean error function of the shear strength parameters according to the shear strength parameters;
constructing a sliding surface position error function according to sliding surface observation information of first destabilization of a target sliding surface and a critical sliding surface determined by finite difference numerical simulation calculation;
sampling the shear strength parameters, obtaining landslide stability coefficients through finite difference strength folding and subtracting calculation according to cohesive force data and internal friction angle data obtained by sampling, and constructing a landslide stability coefficient error function;
performing multiple iterations by using a genetic algorithm based on multiple groups of random sampling samples by combining the shear strength parameter mean error function, the sliding surface position error function and the landslide stability coefficient error function to obtain an optimal parameter set, wherein the optimal parameter set comprises optimal effective cohesive force of natural loess, effective internal friction angle of natural loess, effective cohesive force of saturated loess and effective internal friction angle of saturated loess;
according to other parameters of the target landslide and the optimal parameter set, a simulated sliding surface is constructed in a Flac model, and consistency of sliding surface observation information of the simulated sliding surface and first instability of the target landslide is compared;
and under the condition that the consistency characterization is correct, obtaining a stability prediction result of the target landslide through a Flac model, wherein the prediction result comprises a stability coefficient and sliding surface information of subsequent instability.
Optionally, constructing a shear strength parameter mean error function according to the shear strength parameter includes:
respectively calculating the average value and the standard deviation of each of the effective cohesive force of a plurality of groups of natural loess, the effective internal friction angle of a plurality of groups of natural loess, the effective cohesive force of a plurality of groups of saturated loess and the effective internal friction angle of a plurality of groups of saturated loess, and assuming that the average value and the standard deviation are compliant with normal distribution;
and constructing a shear strength parameter mean error function according to the calculated mean value and standard deviation.
Optionally, the constructed shear strength parameter mean error function is:
wherein x is a shear strength parameter vector, mu x As the average value of each parameter,
an inverse matrix of the covariance matrix of each parameter is represented, and T represents a matrix transposition.
Optionally, constructing a sliding surface position error function according to sliding surface observation information of first destabilization of the target sliding surface and a critical sliding surface determined by finite difference numerical simulation calculation, including:
selecting a plurality of characteristic coordinate points on the first destabilizing sliding surface according to the sliding surface observation information of the first destabilizing sliding surface of the target landslide;
determining a plurality of critical sliding surfaces through a plurality of finite difference numerical simulation calculations, and respectively acquiring a plurality of characteristic coordinate points on each critical sliding surface;
and constructing a sliding surface position error function according to the plurality of characteristic coordinate points on the sliding surface which is unstable for the first time and the plurality of characteristic coordinate points on each critical sliding surface.
Optionally, constructing a sliding surface position error function according to sliding surface observation information of first destabilization of the target sliding surface and a critical sliding surface determined by finite difference numerical simulation calculation, including:
according to the slip surface observation information of the first destabilization of the target landslide, 5 characteristic coordinate points on the slip surface of the first destabilization are selected and marked as (a) i ，b i ) Wherein i=1, 2,3,4,5;
determining multiple critical sliding surfaces through multiple finite difference numerical simulation calculations, obtaining 5 characteristic coordinate points on each critical sliding surface, and marking as (x) i ，y i ) Wherein i=1, 2,3,4,5;
according to 5 characteristic coordinate points on the first destabilizing sliding surface and 5 characteristic coordinate points on the critical sliding surface, a sliding surface position error function is constructed as follows:
optionally, the shear strength parameter is sampled, a landslide stability coefficient is obtained through finite difference strength folding and subtracting calculation according to cohesive force data and internal friction angle data obtained through sampling, and a landslide stability coefficient error function is constructed, including:
sampling the shear strength parameter, and obtaining a landslide stability coefficient through finite difference strength folding and subtracting calculation according to cohesive force data and internal friction angle data obtained by sampling;
assuming that the stability coefficient of the target landslide is 1;
the constructed landslide stability coefficient error function is as follows:
f 3 (x)＝(FS(x)-1)
wherein FS is a landslide stability coefficient obtained by finite difference strength folding and subtracting method.
In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method according to the first aspect of the embodiment when executing the computer program.
In a third aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method according to the first aspect of the embodiments.
The beneficial effects are that:
by constructing three functions, namely a shear strength parameter mean error function, a sliding surface position error function and a landslide stability coefficient error function, and combining a genetic algorithm, carrying out iterative computation on a plurality of groups of random sampling samples, an optimal parameter set is obtained, wherein the optimal parameter set comprises an optimal effective cohesive force of natural loess, an optimal effective internal friction angle of natural loess, an optimal effective cohesive force of saturated loess and an optimal effective internal friction angle of saturated loess; and then constructing a simulated sliding surface in the Flac model by utilizing the optimal parameter data and other parameters of the target landslide, comparing the consistency of the simulated sliding surface and the actual sliding surface observation information of the first instability of the target landslide, and obtaining a stability prediction result of the target landslide through the Flac model under the condition that the consistency characterization is correct, wherein the prediction result comprises the stability coefficient of the subsequent instability and the sliding surface information.
According to the method, the slip surface observation information, the shear strength parameter information and the stability coefficient during the first destabilization of the landslide are considered, more optimization constraint conditions are set for the inverse analysis through setting three functions, more reliable inverse analysis results can be obtained, and further the stability state and the critical slip surface of the target landslide can be effectively predicted.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments of the present application will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart illustrating steps of a loess landslide stability prediction method according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a slip surface of a destabilized target slip according to an embodiment of the present application;
FIG. 3 is a flow chart of an inverse analysis process according to an embodiment of the present application;
FIG. 4 is a longitudinal section view of a landslide according to one embodiment of the present application;
fig. 5 is a simulation result of a case where a landslide of dangchuan 2# is not generated according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating convergence of a genetic algorithm according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a Pareto multi-objective optimization result according to an embodiment of the present application;
FIG. 8 is a schematic diagram showing a comparison of a simulated sliding surface and an actual sliding surface in a first destabilization according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of predicted sliding surfaces in a second destabilization according to an embodiment of the present application;
FIG. 10 (a) is a schematic diagram of the instability range obtained by the first round of simulation of the second instability according to an embodiment of the present application;
FIG. 10 (b) is a schematic diagram of the range of instability obtained by a second round of simulation of a second destabilization according to an embodiment of the present application;
fig. 10 (c) is a schematic diagram of the instability range obtained by the third simulation of the second instability according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In order to protect life and property safety of people, the method is particularly important for risk assessment, prevention and control of landslide, and in order to obtain a more reliable anti-analysis result, further effectively predict the stability state and critical sliding surface of the landslide, a loess landslide stability prediction method is provided.
Referring to fig. 1, a flowchart illustrating steps of a loess landslide stability prediction method according to an embodiment of the present invention, as shown in fig. 1, includes the steps of:
s101, acquiring shear strength parameters of a target area, wherein the shear strength parameters comprise data of effective cohesive force of a plurality of groups of natural loess, effective internal friction angles of a plurality of groups of natural loess, effective cohesive force of a plurality of groups of saturated loess and effective internal friction angles of a plurality of groups of saturated loess, and constructing a shear strength parameter mean error function according to the shear strength parameters.
Firstly, the shear strength parameters of the area where the landslide is located, which is subjected to inverse analysis and stability prediction, are obtained, wherein the shear strength parameters comprise data of effective cohesive force of a plurality of groups of natural loess, effective internal friction angle of a plurality of groups of natural loess, effective cohesive force of a plurality of groups of saturated loess and effective internal friction angle of a plurality of groups of saturated loess, the obtained route is not limited in the application, and by collecting and obtaining the effective cohesive force of 27 groups of natural loess, the effective internal friction angle of 27 groups of natural loess, the effective cohesive force of 18 groups of saturated loess and the effective internal friction angle of 18 groups of saturated loess through consulting documents, the obtained shear strength parameters form a data set.
In one embodiment, the present embodiment further provides a method for constructing a shear strength parameter mean error function, including:
respectively calculating the average value and standard deviation of the effective cohesive force of a plurality of groups of natural loess, the effective internal friction angle of a plurality of groups of natural loess and the effective cohesive force of a plurality of groups of saturated loess;
constructing a shear strength parameter mean error function according to the calculated mean value and standard deviation;
illustratively, the shear strength parameter mean error function is constructed as:
wherein x is a shear strength parameter vector, mu x As the average value of each parameter,
an inverse matrix of the covariance matrix of each parameter is represented, and T represents a matrix transposition.
Since the shear strength parameters include the above 4 parameters, and the mean value of each parameter has a different influence, the influence of the mean value of each parameter can be reduced by using a non-deviation model.
S102, constructing a sliding surface position error function according to sliding surface observation information of first destabilization of the target sliding slope and a critical sliding surface determined through finite difference numerical simulation calculation.
In one possible embodiment, the step may comprise the steps of:
s1: selecting a plurality of characteristic coordinate points on the first destabilizing sliding surface according to the first destabilizing sliding surface observation information of the target sliding surface;
s2: determining a plurality of critical sliding surfaces through a plurality of finite difference numerical simulation calculations, and respectively acquiring a plurality of characteristic coordinate points on each critical sliding surface;
in the step, multiple times of finite difference numerical simulation calculation are performed according to multiple groups of parameter data in each iteration process of a genetic algorithm to obtain multiple critical sliding surfaces, then multiple characteristic coordinate points are obtained on each critical sliding surface, and the number of the characteristic coordinate points obtained on each critical sliding surface is the same as the number of the characteristic coordinate points on the sliding surface which is unstable for the first time.
S3: and constructing a sliding surface position error function according to the plurality of characteristic coordinate points on the sliding surface which is unstable for the first time and the plurality of characteristic coordinate points on the critical sliding surface.
Referring to FIG. 2, there is shown a schematic diagram of a sliding surface of a destabilized target landslide, in which, in an actual implementation, the sliding surface is equally divided into four segments in the x-direction based on first destabilized sliding surface observation information of the target landslide, and 5 feature coordinate points (a) can be obtained i ，b i ) Wherein i=1, 2,3,4,5, and the position information of these 5 coordinate points is taken as the position information of the actual sliding surface; the leftmost characteristic coordinate point is a shear outlet position, and the rightmost characteristic coordinate point is a trailing edge pull crack position.
Determining multiple critical sliding surfaces through multiple finite difference numerical simulation calculations, selecting 5 characteristic coordinate points for each critical sliding surface, and marking as (x) i ，y i ) Wherein i=1, 2,3,4,5.
And then according to 5 characteristic coordinate points on the sliding surface which is unstable for the first time and 5 characteristic coordinate points on the critical sliding surface, constructing a sliding surface position error function as follows:
in other embodiments, other values may be set for i.
In the embodiment, the critical sliding surface is extracted through the Flac, specifically, in order to obtain the critical sliding surface of the loess landslide under the given parameter condition, the displacement information of the unit nodes is extracted through the built-in Fish language programming of the Flac, and is imported into the MATLAB, and the sliding unit bodies are identified by using a K-means clustering algorithm, so that the critical sliding surface is extracted.
The goal of the K-means algorithm is to aggregate n objects into K assigned class clusters according to similarity between the objects, each object belonging to and only belonging to one class cluster with the smallest distance from the center of the class cluster. The Euclidean distance of each object to each cluster center is shown as follows:
wherein A is i Represents the ith object, C j Representing the j-th cluster center; a is that i,t The t attribute representing the i-th object, C j,t The jth attribute representing the jth cluster center, t=1, 2, …, m.
And comparing the distances from each object to each cluster center in turn, and distributing the objects to the class clusters closest to the cluster center to obtain k class clusters { S1, S2, …, sk }. The present application considers only node displacement properties, so t=1; its properties can be divided into a nodal displacement and an inode displacement, i.e. k=2.
S103, sampling the shear strength parameters, obtaining a landslide stability coefficient through finite difference strength folding and subtracting calculation according to cohesive force data and internal friction angle data obtained through sampling, and constructing a landslide stability coefficient error function.
And (3) randomly sampling data of shear strength parameters obtained in the step (S101) including effective cohesive force of a plurality of groups of natural loess, effective internal friction angles of a plurality of groups of natural loess, effective cohesive force of a plurality of groups of saturated loess and effective internal friction angles of a plurality of groups of saturated loess to obtain random sampling samples of a genetic algorithm.
In one embodiment, according to cohesive force data and internal friction angle data obtained by random sampling, performing slope stability analysis by using FLAC finite difference software self-contained strength folding and subtracting method, and performing shearing strength parameter folding and subtracting by the following formula until the target landslide reaches a limit balance state, wherein the folding and subtracting coefficient at the moment is the stability coefficient FS of the target landslide, and the specific formula is as follows:
c r ＝c/FS
wherein c is cohesive force data;
is internal friction angle data; c r The adhesion force of the soil body after the folding is reduced; and->
Is the internal friction angle after the folding.
Assuming that the stability coefficient of the target landslide during instability is 1, the constructed landslide stability coefficient error function is:
f 3 (x)＝(FS(x)-1)
wherein FS is a landslide stability coefficient obtained by finite difference strength folding and subtracting method.
In the method, three error functions are written into a genetic algorithm in advance, and corresponding parameters are brought into the error functions in the execution process of the genetic algorithm.
S104, combining the shear strength parameter mean error function, the sliding surface position error function and the landslide stability coefficient error function, and performing multiple iterations by using a genetic algorithm based on multiple groups of random sampling samples to obtain an optimal parameter set, wherein the optimal parameter set comprises an optimal effective cohesive force of natural loess, an optimal inner friction angle of natural loess, an optimal cohesive force of saturated loess and an optimal inner friction angle of saturated loess.
The genetic algorithm employed in this example is the NSGA-II genetic algorithm, which is a fast non-dominant multi-objective optimized genetic algorithm based on Pareto optimal solution and with elite retention strategy. The method mainly comprises the following three computing parts:
1. pareto solution set fast non-dominant ordering;
2. calculating a crowding degree and a crowding degree comparison operator;
3. and (5) performing cross iteration, and screening optimal parameter points by using elite retention strategies by using the superior and inferior jigs.
And continuously repeating the three steps, finally achieving the target iterative calculation times or convergence conditions, solving the optimal Pareto solution set and outputting.
Referring to fig. 3, a flowchart illustrating an inverse analysis process provided in an embodiment of the present application is shown, first, 100 sets of random sampling samples are constructed, where each set of random sampling samples includes four sample parameters including an effective cohesive force of natural loess, an effective internal friction angle of natural loess, an effective cohesive force of saturated loess, and an effective internal friction angle of saturated loess, and a sampling range of each parameter in the 100 sets of random sampling samples in the genetic algorithm may be a range from a minimum value to a maximum value of a corresponding parameter in a data set formed by shear strength parameters, and 100 sets of values of each parameter in each set of random sampling samples obey a normal distribution of the average value and the standard deviation calculated in step S101.
When the initial iteration number n=0, respectively performing numerical simulation in the Flac model according to 100 groups of random sampling samples, and respectively inputting the simulation results into the shear strength parameter mean error function f 1 (x) The first function value is obtained, 100 groups of random sampling sample numerical simulation calculation are carried into sliding surface position error function f respectively 2 (x) The second function value is obtained, and the stability coefficient calculation data obtained by numerical simulation calculation are respectively brought into a stability coefficient error function f 3 (x) Obtaining a third function value, constraining by three functions, inputting the obtained calculation result into the step of cross variation in the genetic algorithm, and performing optimization calculation on the sample by using the three function values when n=1 iterations are performed, and guiding the iteration times n=n by circulating max ，n max The target iteration number is set in a self-defining mode, and a Pareto solution set is output at the moment, wherein the Pareto solution set comprises values of three functions.
The genetic algorithm reserves 10 relatively optimal samples according to the initial 100 groups of randomly sampled samples through the calculation result of three optimization functions, then randomly samples 90 groups of samples, forms 100 groups of samples by 10 relatively optimal samples and 90 groups of newly extracted samples together, continues to constraint through the three optimization functions, and repeatedly performs the steps until the repetition is completed to obtain an optimal Pareto solution set, and the optimal point can be selected from the optimal Pareto solution set; the three error functions are written into the genetic algorithm in advance, and the corresponding parameters are brought into according to a plurality of groups of samples during each iteration.
Three functions are constructed in the method, so the Pareto solution set of the present application should be a three-dimensional coordinate system. If the level of a group of non-dominant Pareto solutions is defined as 1, the non-dominant Pareto solutions are removed from the solution set, the Pareto solution level is defined as 2 in the rest of the solution set, and the above process is repeated until all the Pareto solution set levels are divided, the level of all the Pareto solutions in the solution set can be obtained, wherein when the target iterative calculation times or convergence condition is reached, the Pareto solution closest to the origin of coordinates is the optimal Pareto solution set.
After the optimal Pareto solution set is obtained, the optimal point is required to be selected as the final solution of multi-objective optimization inverse analysis, and the dimensionless method is specifically selected because the error dimensions of the shear strength parameter error, the slip plane error and the stability coefficient are different, so that the dimensionless method is firstly adopted in the embodiment:
in the method, in the process of the invention,
representing a dimensionless Pareto solution set, F i Points on the Pareto solution curve after multi-objective optimization are represented, and n represents the number of points on the Pareto solution set.
In this embodiment, a LINMAP method is selected to determine the optimal point of the Pareto solution set, and the distance from the point in the Pareto solution set to the optimal solution point is calculated first:
where q is the target number,
representing ideal points under q target optimizations.
Finally, the optimal point i is selected final The method comprises the following steps:
i final ＝i∈min(d i+ )
wherein d i+ The distance from the point in the Pareto solution set to the optimal solution point.
After the optimal points of the Pareto solution set are obtained, an optimal parameter set corresponding to the optimal points is determined, wherein the optimal parameter set comprises an optimal effective cohesion of natural loess, an effective internal friction angle of natural loess, an effective cohesion of saturated loess and an effective internal friction angle of saturated loess.
S105, according to other parameters of the target landslide and the optimal parameter set, a simulated sliding surface is constructed in a Flac model, and consistency of sliding surface observation information of the simulated sliding surface and the first instability of the target landslide is compared.
And the other parameters of the target landslide comprise size parameters, structural parameters, seepage parameters and the like, the size parameters, the structural parameters, the seepage parameters and the like are combined with an optimal parameter set, a simulated sliding surface is constructed in the Flac model, and then the simulated sliding surface is compared with first unsteady sliding surface observation information of the target landslide, namely consistency between the simulated sliding surface and an actual sliding surface is judged.
S106, under the condition that the consistency characterization is correct, obtaining a stability prediction result of the target landslide through a Flac model, wherein the prediction result comprises a stability coefficient and sliding surface information of subsequent instability.
By constructing three functions, namely a shear strength parameter mean error function, a sliding surface position error function and a landslide stability coefficient error function, and combining a genetic algorithm, carrying out iterative computation on a plurality of groups of random sampling samples, an optimal parameter set is obtained, wherein the optimal parameter set comprises an optimal effective cohesive force of natural loess, an optimal effective internal friction angle of natural loess, an optimal effective cohesive force of saturated loess and an optimal effective internal friction angle of saturated loess; and then constructing a simulated sliding surface in the Flac model by utilizing the optimal parameter set data and other parameters of the target landslide, comparing the consistency of the simulated sliding surface and the actual sliding surface observation information of the first instability of the target landslide, and obtaining a stability prediction result of the target landslide through the Flac model under the condition that the consistency characterization is correct, wherein the prediction result comprises the stability coefficient of the subsequent instability and the sliding surface information. In one embodiment, in addition to predicting the stability of a target landslide, a similar landslide may be predicted.
According to the method, the slip surface observation information, the shear strength parameter information and the stability coefficient during the first destabilization of the landslide are considered, more optimization constraint conditions are set for the inverse analysis through setting three functions, more reliable inverse analysis results can be obtained, and further the stability state and the critical slip surface of the target landslide can be effectively predicted.
By way of example, taking the black party Chuan 2# landslide as an example, the method is adopted to conduct inverse analysis on the first destabilization and predict the second destabilization.
The black square table is positioned on the north bank of the Yongjing county yellow river in Gansu province, and the tableland area of the black square table is about 11.5km 2 The black square table is divided into two parts by the tiger wolf ditch with the longest development in the gully: the western area is small, about 1.5km, for square table 2 The method comprises the steps of carrying out a first treatment on the surface of the The eastern area is larger than that of a black table, about 9km 2 . The Dangchuan No. 2 landslide is subjected to two times of static liquefaction type destabilization damages, wherein the length of the first destabilization sliding body is about 20m, the average width is about 115m, and the area is about 8396m 2 The method comprises the steps of carrying out a first treatment on the surface of the The second destabilization involved 3-wheel slip with a total area of about 27422m 2 。
A1: and constructing the Flac model according to the Party Chuan 2# landslide.
Referring to fig. 4, a longitudinal section of a landslide is shown, wherein the lithology of the landslide stratum is loess from top to bottom, and the thickness is about 20-50m; powdery clay with a thickness of about 4-20m; a sandy pebble layer, about 1-8m thick; mudstone and sandy mudstone, and the attitude is 135 degrees and 11 degrees.
Referring to fig. 5, a simulation result when a landslide of dangchuan # 2 does not occur is shown, and the landslide instability damage mainly occurs in a yellow soil layer, and a powdery clay layer is partially scraped during movement, so that the yellow soil layer and a part of powdery clay layer are selected to establish a Flac model, the model is 50m high, 260m wide up, and 300m wide down, and a constant head boundary is adopted.
The seepage mode of the black square platform area is complex, and is the combination of matrix seepage and dominant seepage, because of the poor water seepage of the powdery clay, groundwater is enriched at the bottom of loess and seeps along the platform table edge, when the dominant seepage is used for leading under high irrigation quantity, only dominant seepage is considered, and under the GWflow mode in FLAC, a rapid saturated flow mode is used, so that the loess at the bottom rapidly reaches a saturated state, and high irrigation water flow is simulated to rapidly reach the bottom through gaps and cracks of the loess layer; specifically, the percolation simulation parameters are shown in table 1.
TABLE 1 seepage parameters of soil layers
And obtaining seepage water flow from the junction of the yellow soil layer and the powdery clay layer through seepage simulation, conforming to the actual situation, determining that the yellow soil layer is saturated below the water level line, and finally obtaining the F/ac model of the Dangchuan No. 2 landslide.
A2: and (5) acquiring loess shear strength parameters of the black square platform region, and calculating the mean value and standard deviation of each parameter.
The shear strength parameters, namely the effective cohesion and the effective internal friction angle of the natural loess and the saturated loess are respectively obtained through collecting a large number of sliding belt soil test research results of the black square platform landslide, and are subjected to statistical analysis, mean values and standard deviations are calculated, and the results are shown in Table 2. And the cohesive force of the powdery clay layer is 50kPa, and the internal friction angle is 30 degrees.
TABLE 2 mean and standard deviation of parameters
A3: and constructing three optimization objective functions, namely a shear strength parameter mean error function, a sliding surface position error function and a landslide stability coefficient error function.
A4: and determining the optimal parameter set of the inverse analysis and carrying out inversion.
Referring to fig. 6, a schematic diagram of convergence after the genetic algorithm is iterated 25 times is shown, and referring to fig. 7, a schematic diagram of Pareto multi-objective optimization results is shown; 100 groups of random sampling samples of a genetic algorithm are constructed, the 100 groups of random sampling samples are iterated for 25 times by combining three optimization objective functions, a Pareto solution set of multi-objective optimization is obtained, a LINMAP method is selected to determine the optimal point of the Pareto solution set, and star points in FIG. 7 are the optimal points of the Pareto solution set.
Determining an optimal parameter set of the inverse analysis according to the optimal point of the Pareto solution set, wherein the obtained result is as follows: the effective cohesion of the natural loess is 20.09kPa, and the effective internal friction angle is 22.7 degrees; the effective cohesion of the saturated loess is 12.21kPa, and the effective internal friction is 29.6 degrees; the corresponding stability factor is 0.97.
Referring to fig. 8, a schematic diagram is shown comparing a simulated sliding surface with an actual sliding surface in a first destabilization. Referring to fig. 8, the optimal parameter set is substituted into the Flac model to perform inversion, so as to obtain a corresponding simulated sliding surface, and compared with an actual sliding surface in the first unstable sliding, the comparison shows that although there is a slight difference at the trailing edge of the sliding surface, the critical sliding surface obtained by inverse analysis calculation has better consistency with the actual observed sliding surface.
A5: and predicting the second unsteady sliding of the landslide by using the Flac model to generate a stability prediction result, wherein the stability prediction result comprises sliding surface information and stability coefficients of subsequent unsteady sliding.
Referring to fig. 9, a schematic diagram of predicted sliding surfaces in a second destabilization is shown. Since the interval between the second destabilizing slip and the first destabilizing slip is only about 3 hours, the loess physical mechanical parameters and the water level change are not great in a short time, so that the loess shear strength parameters obtained based on the inverse analysis of the first destabilizing observation information can be ignored, and further, the loess shear strength parameters obtained based on the inverse analysis of the first destabilizing observation information can be used for the second destabilizing slip prediction.
The range of the second unstable sliding is larger and is divided into 3-wheel sliding, the interval time between the 3-wheel sliding is too short, only sliding surface information of the third-wheel sliding is recorded, and the first-wheel sliding and the second-wheel sliding only record trailing edge point position information.
FIG. 10 (a) is a graph showing the range of destabilization obtained by the first round of simulation of the second destabilization, which predicts a stability factor of 1.02;10 (b) a schematic diagram of a destabilization range obtained by a second round of simulation of the second destabilization, wherein the stability coefficient obtained by prediction is 1.01;10 (c) is a schematic diagram of the destabilization range obtained by the third simulation of the second destabilization, and the calculated stability factor obtained by prediction is 1.12.
The prediction result of the second unsteady sliding of the party Chuan 2# landslide is compared with the actual unsteady observation result, the coincidence degree is high, the 3-wheel sliding behavior in the second unsteady sliding is successfully predicted by applying the method, the prediction critical sliding surface is basically consistent with the actual observation sliding surface, and the shape of the third sliding surface is only greatly different. Secondly, the stability coefficients of 3-round instability predictions are all close to 1. Wherein the stability coefficients of the first and second wheel predictions are 1.02 and 1.01, respectively, indicating that the landslide is substantially in an understable state and approaching a limit equilibrium state; the stability factor for the third round of prediction was 1.12, indicating that the landslide is in a substantially steady state.
Through the above examples, the method has excellent anti-analysis results and prediction results, and obtains more reliable anti-analysis results by combining three optimization objective functions, namely, a shear strength parameter mean error function, a sliding surface position error function and a landslide stability coefficient error function, so that the stability of a subsequent landslide is predicted more accurately.
The embodiment of the application also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the method of the embodiment when executing the computer program.
The embodiment of the application is a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the embodiment.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, 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 stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function 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.
While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the present application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The principles and embodiments of the present application are described herein with specific examples, the above examples being provided only to assist in understanding the methods of the present application and their core ideas; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (8)
1. A loess landslide stability prediction method, characterized in that the method comprises:
acquiring shear strength parameters of a target area, wherein the shear strength parameters comprise data of effective cohesive force of a plurality of groups of natural loess, effective internal friction angles of a plurality of groups of natural loess, effective cohesive force of a plurality of groups of saturated loess and effective internal friction angles of a plurality of groups of saturated loess, and constructing a mean error function of the shear strength parameters according to the shear strength parameters;
constructing a sliding surface position error function according to sliding surface observation information of first destabilization of a target sliding surface and a critical sliding surface determined by finite difference numerical simulation calculation;
sampling the shear strength parameters, obtaining landslide stability coefficients through finite difference strength folding and subtracting calculation according to cohesive force data and internal friction angle data obtained by sampling, and constructing a landslide stability coefficient error function;
performing multiple iterations by using a genetic algorithm based on multiple groups of random sampling samples by combining the shear strength parameter mean error function, the sliding surface position error function and the landslide stability coefficient error function to obtain an optimal parameter set, wherein the optimal parameter set comprises optimal effective cohesive force of natural loess, effective internal friction angle of natural loess, effective cohesive force of saturated loess and effective internal friction angle of saturated loess;
according to other parameters of the target landslide and the optimal parameter set, a simulated sliding surface is constructed in a Flac model, and consistency of sliding surface observation information of the simulated sliding surface and first instability of the target landslide is compared, wherein the other parameters comprise a size parameter, a structural parameter and a seepage parameter;
and under the condition that the consistency characterization is correct, obtaining a stability prediction result of the target landslide through a Flac model, wherein the prediction result comprises a stability coefficient and sliding surface information of subsequent instability.
2. The method of claim 1, wherein constructing a shear strength parameter mean error function from the shear strength parameters comprises:
respectively calculating the average value and the standard deviation of each of the effective cohesive force of a plurality of groups of natural loess, the effective internal friction angle of a plurality of groups of natural loess, the effective cohesive force of a plurality of groups of saturated loess and the effective internal friction angle of a plurality of groups of saturated loess, and assuming that the average value and the standard deviation are compliant with normal distribution;
and constructing a shear strength parameter mean error function according to the calculated mean value and standard deviation.
3. The method according to claim 2, wherein the shear strength parameter mean error function is constructed as:
wherein x is a shear strength parameter vector, mu x As the average value of each parameter,
an inverse matrix of the covariance matrix of each parameter is represented, and T represents a matrix transposition.
4. The method of claim 1, wherein constructing a slip position error function from slip observations of a first destabilization of a target slip and a critical slip determined by finite difference numerical simulation calculations comprises:
selecting a plurality of characteristic coordinate points on the first destabilizing sliding surface according to the sliding surface observation information of the first destabilizing sliding surface of the target landslide;
determining a plurality of critical sliding surfaces through a plurality of finite difference numerical simulation calculations, and respectively acquiring a plurality of characteristic coordinate points on each critical sliding surface;
and constructing a sliding surface position error function according to the plurality of characteristic coordinate points on the sliding surface which is unstable for the first time and the plurality of characteristic coordinate points on each critical sliding surface.
5. The method of claim 1, wherein constructing a slip position error function from slip observations of a first destabilization of a target slip and a critical slip determined by finite difference numerical simulation calculations comprises:
according to the slip surface observation information of the first destabilization of the target landslide, 5 characteristic coordinate points on the slip surface of the first destabilization are selected and marked as (a) i ，b i ) Wherein i=1, 2,3,4,5;
determination of critical slip by multiple finite difference numerical simulation calculationsA moving surface, 5 characteristic coordinate points on each critical sliding surface are obtained and marked as (x) i ，y i ) Wherein i=1, 2,3,4,5;
according to 5 characteristic coordinate points on the sliding surface of the first destabilization and 5 characteristic coordinate points on the critical sliding surface, the constructed sliding surface position error function is as follows:
6. the method of claim 1, wherein sampling the shear strength parameter, calculating a landslide stability coefficient by finite difference strength folding and subtracting from the cohesive force data and the internal friction angle data obtained by sampling, and constructing a landslide stability coefficient error function, comprising:
sampling the shear strength parameter, and obtaining a landslide stability coefficient through finite difference strength folding and subtracting calculation according to cohesive force data and internal friction angle data obtained by sampling;
assuming that the stability coefficient of the target landslide is 1;
the constructed landslide stability coefficient error function is as follows:
f 3 (x)＝(FS(x)-1)
wherein FS is a landslide stability coefficient obtained by finite difference strength folding and subtracting method.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any one of claims 1 to 6 when executing the computer program.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146901.6A CN114692441B (en) | 2022-02-17 | 2022-02-17 | Loess landslide stability prediction method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146901.6A CN114692441B (en) | 2022-02-17 | 2022-02-17 | Loess landslide stability prediction method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114692441A CN114692441A (en) | 2022-07-01 |
| CN114692441B true CN114692441B (en) | 2023-05-09 |
Family
ID=82136953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210146901.6A Active CN114692441B (en) | 2022-02-17 | 2022-02-17 | Loess landslide stability prediction method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114692441B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879325B (en) * | 2023-02-22 | 2023-06-09 | 西南交通大学 | Sliding surface shear strength parameter inversion method, device, equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408944A (en) * | 2018-10-19 | 2019-03-01 | 河海大学 | Expansive soil slope failure by leaking method for analyzing stability based on complete softening intensity |
| CN110457651A (en) * | 2019-07-05 | 2019-11-15 | 中国地质大学（武汉） | It is a kind of to utilize the improved Prediction of Displacement in Landslide method of data assimilation |
| CN111914481A (en) * | 2020-07-27 | 2020-11-10 | 山西大学 | Slope stability prediction method based on improved PSO-RBF algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10330661B2 (en) * | 2015-09-14 | 2019-06-25 | Nec Corporation | Disaster prediction system, moisture prediction device, disaster prediction method, and program recording medium |
-
2022
- 2022-02-17 CN CN202210146901.6A patent/CN114692441B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408944A (en) * | 2018-10-19 | 2019-03-01 | 河海大学 | Expansive soil slope failure by leaking method for analyzing stability based on complete softening intensity |
| CN110457651A (en) * | 2019-07-05 | 2019-11-15 | 中国地质大学（武汉） | It is a kind of to utilize the improved Prediction of Displacement in Landslide method of data assimilation |
| CN111914481A (en) * | 2020-07-27 | 2020-11-10 | 山西大学 | Slope stability prediction method based on improved PSO-RBF algorithm |
Non-Patent Citations (2)
| Title |
|---|
| Image-Data-Driven Slope Stability Analysis for Preventing Landslides Using Deep Learning;Behnam Azmoon等;《IEEE Access》;第150623-150636页 * |
| 兰州石峡口地区斜坡稳定性趋势预测;徐秀娟;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;第C038-305页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114692441A (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jin et al. | Multi-objective optimization-based updating of predictions during excavation | |
| Moghaddasi et al. | ICA-ANN, ANN and multiple regression models for prediction of surface settlement caused by tunneling | |
| CN108256177B (en) | Parameter optimization method and system for river water sand model | |
| Gholami et al. | Uncertainty analysis of intelligent model of hybrid genetic algorithm and particle swarm optimization with ANFIS to predict threshold bank profile shape based on digital laser approach sensing | |
| US11295048B2 (en) | Machine learning assisted reservoir simulation | |
| Sun et al. | A multiscale flaw detection algorithm based on XFEM | |
| Wu et al. | Prediction of stress intensity factors in pavement cracking with neural networks based on semi-analytical FEA | |
| Majdi et al. | Applying evolutionary optimization algorithms for improving fuzzy C-mean clustering performance to predict the deformation modulus of rock mass | |
| Roushangar et al. | Evaluation of genetic programming-based models for simulating friction factor in alluvial channels | |
| CN111210519A (en) | High core rock-fill dam deformation parameter inversion method | |
| CN107451383B (en) | Calibration method for initial bed sand gradation of plane two-dimensional water sand mathematical model | |
| CN106019394B (en) | Three-dimensional parallel inversion method for nonlinear conjugate gradient of ocean magnetotelluric field | |
| CN114692441B (en) | Loess landslide stability prediction method, electronic equipment and storage medium | |
| CN113158315A (en) | Rock-soil body parameter three-dimensional non-stationary condition random field modeling method based on static cone penetration data | |
| Sivrikaya et al. | Estimation of compaction parameters of fine‐grained soils in terms of compaction energy using artificial neural networks | |
| Hasheminejad et al. | Predicting the collapsibility potential of unsaturated soils using adaptive neural fuzzy inference system and particle swarm optimization | |
| CN112084655A (en) | Ground penetrating radar parameter inversion method based on non-monotonic line search | |
| CN106537461B (en) | Geomechanical modeling using dynamic boundary conditions from time-shifted data | |
| CN115238549B (en) | Method for monitoring safety coefficient under landslide rainfall condition by using ERT | |
| Lieberman et al. | Nonlinear goal-oriented Bayesian inference: application to carbon capture and storage | |
| Christelis et al. | Employing surrogate modelling for the calibration of a 2D flood simulation model | |
| Sun et al. | A two-scale algorithm for detection of multiple flaws in structures modeled with XFEM | |
| Rengers et al. | Application of an evolutionary algorithm for parameter optimization in a gully erosion model | |
| CN114996947A (en) | Three-dimensional oil reservoir numerical simulation method | |
| CN113642785A (en) | Method, system and equipment for long-term prediction of space debris orbit based on prior information |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |