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

Method for predicting subsidence of soil outside pit based on differential evolution support vector machine

A technology of support vector machine and differential evolution algorithm, applied in special data processing applications, instruments, electrical digital data processing and other directions, can solve problems such as complex underground pipelines

Inactive Publication Date: 2013-07-10
LIAONING TECHNICAL UNIVERSITY
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Foundation pits are one of them. The foundation pits of urban subways are often surrounded by many buildings and complex underground pipelines. If the degree of settlement is not predicted and discovered in time, it may cause serious consequences.

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
  • Method for predicting subsidence of soil outside pit based on differential evolution support vector machine
  • Method for predicting subsidence of soil outside pit based on differential evolution support vector machine
  • Method for predicting subsidence of soil outside pit based on differential evolution support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Use the foundation pit data of Dalian Metro Wanjia Station for specific implementation.

[0061] Realize the DE algorithm in the Matlab environment, the ( , ) input as a parameter, ( A , O ) as the number of optimization variables, n =2, population number PN is 30, and the last 10 points are used as prediction inspection points. Choose different scaling factors and hybridization probability constants, F =0.1:0.1:1.0, Cr =0.1:0.1:1.0, a total of 100 cases.

[0062] From figure 2 It can be seen that 100 cases can converge quickly under a small number of iterations, and the convergence rate is 98%. There are two cases that do not converge, and the corresponding parameter ranges are:

[0063] ;

[0064] .

[0065] take here F =0.6, Cr =0.6; the parameters obtained after inversion are: A =0.8100; O =0.0022, bring the data into Expressed as follows:

[0066]

[0067] Fit Curve Image plot with the original discrete data compare, such as ima...

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 discloses a method for predicting subsidence of soil outside a pit based on a differential evolution support vector machine. The method comprises collection of the subsidence of on-site soil outside the pit, determination of a rough change rule of data to be a tangent curve, tangent fitting on subsidence data through differential evolution (DE), reasonable selection method of a scaling factor F and a crossover probability Cr of the DE, determination of a decision function of the support vector machine (SVM), simulation of generation of the subsidence data, evaluation and the like. The method comprises the following steps: through the DE, determining the basic form of a subsidence function for the soil outside the pit according to the subsidence data, and then performing parametric inversion; taking an obtained analytic function as the decision function of the SVM, and performing kernel function conversion on the decision function by the SVM; and finally, performing fitting prediction through the SVM, and detecting data conformity. Through the subsidence data of the on-site soil and the subsidence prediction simulation, curve fitting of the SVM is quicker and the prediction is more accurate; and the method can be widely applied to safety monitoring on foundation pit construction.

Description

technical field [0001] The invention relates to the monitoring and prediction of the settlement of the soil outside the pit during the foundation pit construction in geotechnical engineering, in particular to the prediction of the settlement of the soil outside the pit by a differential evolution support vector machine algorithm. Background technique [0002] With the large-scale construction of subway projects, the soil deformation caused by the construction process of various related subjects has received great attention. Foundation pits are one of them. The foundation pits of urban subways are often surrounded by many buildings and complex underground pipelines. If the degree of settlement is not predicted and discovered in time, serious consequences may result. [0003] Many methods are currently used to analyze and predict foundation pit soil settlement, mainly including finite element analysis based on soil constitutive model, corresponding analysis based on input valu...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F19/00
Inventor 刘文生吴作启崔铁军由丽雯杨逾邵军张媛孙琦杜东宁
Owner LIAONING TECHNICAL UNIVERSITY
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