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

Gravel soil earthquake liquefaction discrimination method based on Bayesian network

A technology of Bayesian network and discriminant method, applied in the direction of probability network, neural learning method, biological neural network model, etc., which can solve the problems of insufficient precision and poor applicability, so as to enhance the generalization ability, expand the scope of application, Effects that improve effectiveness and accuracy

Pending Publication Date: 2021-03-16
CHINA THREE GORGES UNIV
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to respond to the actual needs of liquefaction discrimination in gravel soil sites in engineering, solve the problems of insufficient accuracy and wide applicability of existing discrimination methods

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
  • Gravel soil earthquake liquefaction discrimination method based on Bayesian network
  • Gravel soil earthquake liquefaction discrimination method based on Bayesian network
  • Gravel soil earthquake liquefaction discrimination method based on Bayesian network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as Figure 1-3 As shown, a gravel earth seismicization discriminant method based on the Bayesian network, which includes the following steps:

[0033] Step 1: Select key factors from many gravel earthquake liquefaction factors, as a discriminant indicator of gravel earthquake liquefaction;

[0034] Step 2: According to the selected discrimination indicator, collect the historical data of the gravel earthquake liquefaction site, and divide the data into training set data sets and test set data sets;

[0035] Step Three: using the training set data and the Bayesian network structure learning parameter learning generating method of Liquefaction land gravel, grit build dependencies between Liquefaction Soil Soil liquefaction potential index and gravel;

[0036] Step 4: Based on the test set data, the resulting gravel earthquake liquefaction discriminant method is verified and the performance evaluation index of the method is obtained.

[0037] Further, the Bayesian network ...

Embodiment 2

[0046] Embodiment 1 of the present invention provides a method of gravel earthquake liquefaction discriminant based on Bayesian network, such as figure 1 According to the technical roadmap, the specific steps are as follows:

[0047] 205 groups of historical earthquake liquefaction survey data based on power tenture test, considering 12 gravel earthquake liquefaction discriminant indicators (magnitude M w , Epicenter distance R, earthquake holding time T, peak acceleration PGA, gravel content GC, fine particle content Fc, average particle size D 50 , Correction power penetration hammer number N 1 ' 20 , Overlying effective soil pressure σ v ', Groundwater buried deep D w , Thickness of the upper layer n Non-saturated soil layer thickness between groundwater level and overlying water n ), The above 12 discriminant indicators are used as the input node, and the gravel earthquake liquefaction will be used as the output node, and the Bayesian network method of the gravel earthquake l...

Embodiment 3

[0054] The present invention provides a method of gravel earthzer liquefaction discriminating based on a Bayesian network, which is substantially identical to the first embodiment, and is different, and the correction of the correction power in the discriminator is N. 1 ' 20 Replace with the correction shear wave speed V s1 And use 205 sets of shear wave velocity history survey data to learn the structure and parameter learning.

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 gravel soil earthquake liquefaction discrimination method based on a Bayesian network, which comprises the following steps: 1, selecting a key factor from a plurality of gravel soil earthquake liquefaction influence factors, and enabling the key factor to serve as a discrimination index of gravel soil earthquake liquefaction; 2, according to the selected discrimination indexes, collecting gravel soil seismic liquefaction site historical data, and dividing the data into a training set data set and a test set data set; 3, performing structure learning and parameter learning of the Bayesian network by utilizing the training set data, generating a gravel soil seismic liquefaction discrimination method, and constructing a dependency relationship between gravel soil liquefaction discrimination indexes and gravel soil liquefaction potential; and step 4, based on the test set data, verifying the obtained gravel soil seismic liquefaction discrimination method, and obtaining performance evaluation indexes of the method. The method can solve the problems of insufficient precision, narrow applicability and the like of an existing discrimination method.

Description

Technical field [0001] The present invention belongs to the field of earthquake resistance technology, and more particularly to a method of liquefaction discrimination based on the gravel soil of Bayesian network. Background technique [0002] Earthquake liquefaction is an important issue that cannot be ignored in the field of earthquake earthquake. It refers to saturated sand soil, a saturated light sub-clay and cascade of a highly cobin content, which may occur under seismic power. LNG, so that the soil strength is greatly lost. Seismic disasters have occurred in many earthquakes in history, such as Japanese Niigi earthquake in 1964, the Alaska earthquake in the United States, my country's 2008 Wenchuan Earthquake and 2018 Indonesian Sulawesi Earthquake, etc. Seismic liquefaction disasters cause serious life and property damage. In view of this, the relevant studies of seismic disaster prevention and control have been continued in the field of engineering. [0003] Earthquake l...

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): G06K9/62G06N3/08G06N7/00
CPCG06N3/08G06N7/01G06F18/214
Inventor 胡记磊张政邹文君谈云志
Owner CHINA THREE GORGES UNIV
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