Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Side slope reliability analysis method based on MRVM-AFOSM

An analysis method and reliability technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of available variance, sparse model structure, and few required parameters, and achieve the best fitting and prediction capabilities , accurate calculation results and fast calculation speed

Inactive Publication Date: 2017-10-10
XIAN UNIV OF TECH
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Compared with SVM, RVM has the advantages of sparse model structure, relatively low computational complexity, can provide variance, requires few parameters, and kernel function does not need to meet Mercer conditions. However, although RVM can accurately calculate the safety factor Estimated, but due to the shortcomings of MVFOSM itself, the calculation error of RVM-MVFOSM reliability is obvious

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Side slope reliability analysis method based on MRVM-AFOSM
  • Side slope reliability analysis method based on MRVM-AFOSM
  • Side slope reliability analysis method based on MRVM-AFOSM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, the calculation flow chart of slope reliability analysis method based on MRVM-AFOSM, which specifically includes the following steps:

[0052] Step 1. Identify each impact factor X i The distribution form of (i=1,2,...,k) constructs the input factor of the sample, and the influence factor is a factor that affects the stability of the slope, and then adopts the traditional slope stability factor of safety method to calculate the sample safety factor (this embodiment Use the Bishop method in the limit equilibrium method to calculate the safety factor of slope stability), and use the sample safety factor as the output factor of the sample; the sample is divided into training samples and test samples;

[0053] Step 2. Construct the hybrid kernel function MRVM, use the HS algorithm to optimize the kernel parameter value, and use the training samples to train the MRVM;

[0054] MRVM is an improvement and extension of the kernel function of RVM, an...

Embodiment 2

[0120] In order to contrast with RVM-FOSM, this embodiment calculates the reliability of a single-layer slope, the shape of the slope is as follows image 3 As shown, the calculation mainly considers rock cohesion C, internal friction coefficient The influence of rock bulk density γ on slope safety and stability, the average values ​​are: C=12kN / m 2 , γ=19.06kN / m 3 . Assuming that the independent variables are all non-correlated normal distributions, the reliability of slope stability is calculated when the coefficients of variation are 0.05%, 0.10%, and 0.15%, respectively. For comparison, all sample data are from literature (Bucher CG, Bourgund U.A fast and efficient responsesurface approach for structural reliability problems. Struct Safety 1990; 7:57–66). There are 40 groups of samples in total, and the first 28 groups are training samples, which mainly complete the training task of MRVM. The latter 12 groups are test samples for testing the fitting effect of MRVM. ...

Embodiment 3

[0134] On the basis of the above-mentioned embodiment, in order to contrast with SVM-FOSM, this embodiment calculates the reliability of a certain multi-layer slope, the shape of the slope is shown in Figure 7 . The slope is divided into three layers, and the material parameters of each layer are shown in Table 4. It is assumed that the independent variables are all non-correlated normal distributions.

[0135] Table 4

[0136]

[0137] Since the original article did not provide samples, this article puts each variable in Latin hypercube sampling is performed in the range to generate 48 groups of samples, of which 36 groups are used for training and 12 groups are used for testing. After many trial calculations, the MRVM kernel parameters m=0.9999955, c=15.33301, η=0.73802, r=7.03048, q=1.55978 were finally determined. The average absolute error of the 36 sets of training data was 0.016, and the average relative error was only 1.33%. Fitting effect such as Figure 8 sh...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a side slope reliability analysis method based on MRVM-AFOSM. The method specifically comprises the following steps: explicitly determining a distribution form of each influence factor, constructing a sample and computing a safety coefficient; constructing a hybrid kernel function MRVM, optimizing the kernel parameter value by using a HS algorithm and training the sample; estimating a testing sample by using the trained MRVM and computing the MAE; when the MAE satisfies the error requirement, accomplishing the MRVM training; computing the reliability by using the AFOSM, selecting an initial design checking calculation point, and computing the side slope stability security coefficient and the first-order derivative by using the MRVM to obtain a new design checking calculation point; if the new design checking calculation point satisfies an iterative end condition, ending the iteration to obtain the side slope reliability. The reliability analysis is performed on the side slope stability by using the MRVM-AFOSM, the MRVM explicitly expresses the performance function so as to conveniently resolving the first-order derivative of a limit state function; and then the AFOSM is used for computing the design checking calculation point, thereby obtaining more accurate reliability result.

Description

technical field [0001] The invention belongs to a slope reliability analysis method, in particular to a slope reliability analysis method based on MRVM-AFOSM. Background technique [0002] Slope engineering contains a large number of uncertain factors, and it is difficult to accurately evaluate its safety behavior by conventional deterministic methods. The reliability uses methods such as probability theory and mathematical statistics, and uses various uncertain factors as random variables to analyze the possibility of slope instability, which can more reasonably reflect the actual safety status of the slope. [0003] Traditional slope reliability analysis methods mainly include: first-order reliability method (FORM), second-order reliability method (SORM), response surface method (RSM), Monte Carlo simulation (MCS), etc., among which FORM is divided into Mean First Order Second Moment (MVFOSM) and Improved First Order Second Order (AFOSM). [0004] Although MVFOSM is easy...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/50
CPCG06F30/3323
Inventor 马春辉杨杰胡德秀程琳
Owner XIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com