Correction method for determining bearing capacity of cohesive soil foundation through transverse wave velocity based on BP network

A shear wave velocity, BP network technology, applied in neural learning methods, biological neural network models, special data processing applications, etc., can solve the problems of long test cycle, time-consuming and labor-intensive, limited measurement depth, etc. Time limit, strong applicability and quantification, and the effect of reducing physical workload

Active Publication Date: 2021-08-03
CHINA RAILWAY DESIGN GRP CO LTD +1
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, in-situ testing has a limited depth, which is time-consuming and labor-intensive; the theoretical formula method and the standard table method also rely on the samples obtained from drilling and in-situ test results. Difficulties Encountered in Railway Engi...

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
  • Correction method for determining bearing capacity of cohesive soil foundation through transverse wave velocity based on BP network
  • Correction method for determining bearing capacity of cohesive soil foundation through transverse wave velocity based on BP network
  • Correction method for determining bearing capacity of cohesive soil foundation through transverse wave velocity based on BP network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] Count the shear wave and cohesive soil standard penetration hits of drill holes that have been explored in Northeast China, and collect the corresponding shear wave data in this area. There are 18 drill holes and 53 layers of cohesive soil sample points in this statistics. 8 outliers need to be removed.

[0089] The collected data used normal distribution, and the data outside 99.7% of the probability density function had to be removed.

[0090] Use the shear wave seismograph to collect shear wave data with a point distance of 5m, perform filtering and deconvolution, and finally obtain the shear wave velocity profile in this area through inversion, use sufer software to grid according to the Kriging difference method, and the grid spacing For 5m*5m, use MapGen software to extract the shear wave velocity of bridges, roadbeds and other projects. The interval of shear wave velocity is 5m, and analyze according to the statistical results in Table 1. The mileage of bridges,...

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 provides a correction method for determining the bearing capacity of a cohesive soil foundation through transverse wave velocity based on a BP network. The correction method comprises the steps of acquiring a transverse wave velocity sample value and a standard penetration test blow count sample value of a site; performing regression curve fitting to obtain a first fitting curve; obtaining a transverse wave velocity measured value of the site, inputting the measured value into the BP network, and obtaining a second fitting curve according to a predicted value output by the BP network; and correcting the first fitting curve by using the second fitting curve to obtain a calibration curve, searching the corresponding standard penetration test number, and determining the foundation bearing capacity by using a standard look-up table according to the obtained standard penetration test number and the obtained actually measured void ratio. According to the invention, after linear regression fitting is carried out by using the neural network, nonlinear factors are fully considered, and the fitting curve is corrected. Compared with a conventional exploration method, the method has the advantages that the influence of external factors on the geological exploration progress can be greatly weakened, the workload of in-situ testing of real objects is reduced, and a new technical means is provided for better and faster determination of the bearing capacity of the cohesive soil foundation.

Description

technical field [0001] The invention relates to the technical field of determining the bearing capacity of a high-speed railway cohesive soil foundation, in particular to a correction method for determining the bearing capacity of a cohesive soil foundation based on a BP network based on shear wave velocity. Background technique [0002] Railway construction is changing from quantity-scale type to quality-benefit type, and the construction area is gradually expanding to difficult and complex mountainous areas, forest areas, high-steep terrain, high altitude and other areas. More and more new railways have to pass through complex terrain and geological conditions. At the same time, it is also facing increasing environmental protection and construction period requirements. It is increasingly difficult for conventional exploration methods to meet the high-precision and tight construction period survey requirements of high-speed railways. Not only that, the terrain and geologica...

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): G06F30/13G06F30/20G06N3/08
CPCG06N3/084G06F30/13G06F30/20
Inventor 马元李志华崔庆国杨国俊秦海旭祁晓雨周学明刘永高郭云苗鑫淼
Owner CHINA RAILWAY DESIGN GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products